Notification:
We are currently experiencing intermittent issues impacting performance. We apologize for the inconvenience.
By Topic

Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of

Popular Articles (January 2015)

Includes the top 50 most frequently downloaded documents for this publication according to the most recent monthly usage statistics.
  • 1. Deep Learning-Based Classification of Hyperspectral Data

    Publication Year: 2014 , Page(s): 2094 - 2107
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2730 KB) |  | HTML iconHTML  

    Classification is one of the most popular topics in hyperspectral remote sensing. In the last two decades, a huge number of methods were proposed to deal with the hyperspectral data classification problem. However, most of them do not hierarchically extract deep features. In this paper, the concept of deep learning is introduced into hyperspectral data classification for the first time. First, we verify the eligibility of stacked autoencoders by following classical spectral information-based classification. Second, a new way of classifying with spatial-dominated information is proposed. We then propose a novel deep learning framework to merge the two features, from which we can get the highest classification accuracy. The framework is a hybrid of principle component analysis (PCA), deep learning architecture, and logistic regression. Specifically, as a deep learning architecture, stacked autoencoders are aimed to get useful high-level features. Experimental results with widely-used hyperspectral data indicate that classifiers built in this deep learning-based framework provide competitive performance. In addition, the proposed joint spectral-spatial deep neural network opens a new window for future research, showcasing the deep learning-based methods' huge potential for accurate hyperspectral data classification. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 2. Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion Contest

    Publication Year: 2014 , Page(s): 2405 - 2418
    Cited by:  Papers (3)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4148 KB)  

    The 2013 Data Fusion Contest organized by the Data Fusion Technical Committee (DFTC) of the IEEE Geoscience and Remote Sensing Society aimed at investigating the synergistic use of hyperspectral and Light Detection And Ranging (LiDAR) data. The data sets distributed to the participants during the Contest, a hyperspectral imagery and the corresponding LiDAR-derived digital surface model (DSM), were acquired by the NSF-funded Center for Airborne Laser Mapping over the University of Houston campus and its neighboring area in the summer of 2012. This paper highlights the two awarded research contributions, which investigated different approaches for the fusion of hyperspectral and LiDAR data, including a combined unsupervised and supervised classification scheme, and a graph-based method for the fusion of spectral, spatial, and elevation information. View full abstract»

    Open Access
  • 3. Multi-Modal and Multi-Temporal Data Fusion: Outcome of the 2012 GRSS Data Fusion Contest

    Publication Year: 2013 , Page(s): 1324 - 1340
    Cited by:  Papers (3)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4023 KB) |  | HTML iconHTML  

    The 2012 Data Fusion Contest organized by the Data Fusion Technical Committee (DFTC) of the IEEE Geoscience and Remote Sensing Society (GRSS) aimed at investigating the potential use of very high spatial resolution (VHR) multi-modal/multi-temporal image fusion. Three different types of data sets, including spaceborne multi-spectral, spaceborne synthetic aperture radar (SAR), and airborne light detection and ranging (LiDAR) data collected over the downtown San Francisco area were distributed during the Contest. This paper highlights the three awarded research contributions which investigate (i) a new metric to assess urban density (UD) from multi-spectral and LiDAR data, (ii) simulation-based techniques to jointly use SAR and LiDAR data for image interpretation and change detection, and (iii) radiosity methods to improve surface reflectance retrievals of optical data in complex illumination environments. In particular, they demonstrate the usefulness of LiDAR data when fused with optical or SAR data. We believe these interesting investigations will stimulate further research in the related areas. View full abstract»

    Open Access
  • 4. Development of a Highly Flexible Mobile GIS-Based System for Collecting Arable Land Quality Data

    Publication Year: 2014 , Article#: 2320635
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (2014 KB) |  | HTML iconHTML  

    In recent years, well-designed terminal-based methods for collecting index data have gradually replaced traditional pen-and-paper methods and have been extensively used in numerous studies. These new approaches offer users increased accuracy, efficiency, consumption, and data compatibility compared to traditional methods. In general, we find that spatial data content and quality index systems vary widely across different arable land regions. Thus, a system for the investigation of arable land quality indices that has the flexibility to utilize various types of spatial data and quality indices without requiring program modification is needed. This paper presents the framework, the module partition, and the structure of the data exchange interface for a highly flexible mobile GIS-based system, which we call the “arable land quality index data collection system” (ALQIDCS). This system incorporates a series of self-adaptive methods, a data table-driven model and two types of formulas for flexible data collection and processing. We tested our prototype system by investigating arable land quality in the Da Xing District, Beijing and in the Te Da La Qi District, Inner Mongolia, China. The results indicate that the ALQIDCS can effectively adapt to variations in spatial data and quality index systems and meet different objectives. The limitations of the ALQIDCS and suggestions for future work are also presented. View full abstract»

    Open Access
  • 5. Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches

    Publication Year: 2012 , Page(s): 354 - 379
    Cited by:  Papers (118)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3629 KB) |  | HTML iconHTML  

    Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution enables material identification via spectroscopic analysis, which facilitates countless applications that require identifying materials in scenarios unsuitable for classical spectroscopic analysis. Due to low spatial resolution of HSCs, microscopic material mixing, and multiple scattering, spectra measured by HSCs are mixtures of spectra of materials in a scene. Thus, accurate estimation requires unmixing. Pixels are assumed to be mixtures of a few materials, called endmembers. Unmixing involves estimating all or some of: the number of endmembers, their spectral signatures, and their abundances at each pixel. Unmixing is a challenging, ill-posed inverse problem because of model inaccuracies, observation noise, environmental conditions, endmember variability, and data set size. Researchers have devised and investigated many models searching for robust, stable, tractable, and accurate unmixing algorithms. This paper presents an overview of unmixing methods from the time of Keshava and Mustard's unmixing tutorial to the present. Mixing models are first discussed. Signal-subspace, geometrical, statistical, sparsity-based, and spatial-contextual unmixing algorithms are described. Mathematical problems and potential solutions are described. Algorithm characteristics are illustrated experimentally. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 6. Assessing Agricultural Water Productivity in Desert Farming System of Saudi Arabia

    Publication Year: 2015 , Article#: 2320592
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (3384 KB) |  | HTML iconHTML  

    The primary objective of this study was to assess the water productivity (WP) of the annual (wheat, barley, and corn) and biennial (alfalfa and Rhodes grass) crops cultivated under center-pivot irrigation located over desert areas of the Al-Kharj region in Saudi Arabia. The Surface Energy Balance Algorithm for Land (SEBAL) was applied to Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images to obtain evapotranspiration (ET) for assessing WP and irrigation performance (IP) of crops. Crop productivity (CP) was estimated using Normalized Difference Vegetation Index (NDVI) crop productivity models. The predicted CP ( {\bf{\rm CP}_{\rm P}} ) for corn varied from 12 690 to 14 060 kg/ha and from 6000 to 7370 kg/ha for wheat. The {{\rm CP}_{\rm P}} for alfalfa and Rhodes grass was 42 450 and 58 210 (kg/ha/year), respectively. The highest predicted WP was observed in wheat ( {\bf 0.80{-}2.01nbsp\hbox {kg}/\hbox {m}^3} ) and the lowest was in alfalfa ( {\bf {0.38{-}0.46nbsp\hbox {kg}/\hbox {m}}^3} ). The deviation between SEBAL predicted ET ( {\bf {\rm ET}_{\rm P}} ) and weather station recorded ET ( {\bf {\rm ET}_{\rm W}} ) was 10%. The performance of the prediction models was assessed against the measured data. The overall mean bias/error of the predictions of CP, ET, and WP was 9.4%,  {\bf {-} 2.68%} , and 9.65%, respectively; the root mean square error (RMSE) was 1996 (kg/ha), 2107 ( {\bf \hbox {m}^3- \hbox {ha}} ), and 0.09 ( {\bf\hbox {kg}/\hbox {m}^3} ) for CP, ET, and WP, respectively. When CP was converted into variations between the actual and predicted, the variations were 8% to 12% for wheat, 14% to 20% for corn, 17% to 35% for alfalfa, 3% to 38% for Rhodes grass, and 4% for barley. View full abstract»

    Open Access
  • 7. Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems

    Publication Year: 2009 , Page(s): 2 - 10
    Cited by:  Papers (52)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1056 KB) |  | HTML iconHTML  

    The contribution of power production by photovoltaic (PV) systems to the electricity supply is constantly increasing. An efficient use of the fluctuating solar power production will highly benefit from forecast information on the expected power production. This forecast information is necessary for the management of the electricity grids and for solar energy trading. This paper presents an approach to predict regional PV power output based on forecasts up to three days ahead provided by the European Centre for Medium-Range Weather Forecasts (ECMWF). Focus of the paper is the description and evaluation of the approach of irradiance forecasting, which is the basis for PV power prediction. One day-ahead irradiance forecasts for single stations in Germany show a rRMSE of 36%. For regional forecasts, forecast accuracy is increasing in dependency on the size of the region. For the complete area of Germany, the rRMSE amounts to 13%. Besides the forecast accuracy, also the specification of the forecast uncertainty is an important issue for an effective application. We present and evaluate an approach to derive weather specific prediction intervals for irradiance forecasts. The accuracy of PV power prediction is investigated in a case study. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 8. An Area-Based Image Fusion Scheme for the Integration of SAR and Optical Satellite Imagery

    Publication Year: 2013 , Page(s): 2212 - 2220
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2032 KB) |  | HTML iconHTML  

    The task of enhancing the perception of a scene by combining information captured from different image sensors is usually known as multisensor image fusion. This paper presents an area-based image fusion algorithm to merge SAR (Synthetic Aperture Radar) and optical images. The co-registration of the two images is first conducted using the proposed registration method prior to image fusion. Segmentation into active and inactive areas is then performed on the SAR texture image for selective injection of the SAR image into the panchromatic (PAN) image. An integrated image based on these two images is generated by the novel area-based fusion scheme, which imposes different fusion rules for each segmented area. Finally, this image is fused into a multispectral (MS) image through the hybrid pansharpening method proposed in previous research. Experimental results demonstrate that the proposed method shows better performance than other fusion algorithms and has the potential to be applied to the multisensor fusion of SAR and optical images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 9. Object-Based Image Analysis and Digital Terrain Analysis for Locating Landslides in the Urmia Lake Basin, Iran

    Publication Year: 2014 , Article#: 2350036
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1351 KB) |  | HTML iconHTML  

    The main objective of this research was to establish a semiautomated object-based image analysis (OBIA) methodology for locating landslides. We have detected and delineated landslides within a study area in north-western Iran using normalized difference vegetation index (NDVI), brightness, and textural features derived from satellite imagery (IRS-ID and SPOT-5) in combination with slope and flow direction derivatives from a digital elevation model (DEM) and topographically oriented gray-level cooccurrence matrices (GLCMs). We utilized particular combinations of these information layers to generate objects by applying multiresolution segmentation in a sequence of feature selection and object classification steps. The results were validated by using a landslide inventory database including 109 landslide events. In this study, a combination of these parameters led to a high accuracy of landslide delineation yielding an overall accuracy of 93.07%. Our results confirm the potential of OBIA for accurate delineation of landslides from satellite imagery and, in particular, the ability of OBIA to incorporate heterogeneous parameters such as DEM derivatives and surface texture measures directly in a classification process. The study contributes to the establishment of geographic object-based image analysis (GEOBIA) as a paradigm in remote sensing and geographic information science. View full abstract»

    Open Access
  • 10. Remote Sensing With Simulated Unmanned Aircraft Imagery for Precision Agriculture Applications

    Publication Year: 2014 , Article#: 2317876
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (776 KB) |  | HTML iconHTML  

    An important application of unmanned aircraft systems (UAS) may be remote-sensing for precision agriculture, because of its ability to acquire images with very small pixel sizes from low altitude flights. The objective of this study was to compare information obtained from two different pixel sizes, one about a meter (the size of a small vegetation plot) and one about a millimeter. Cereal rye (Secale cereale) was planted at the Beltsville Agricultural Research Center for a winter cover crop with fall and spring fertilizer applications, which produced differences in biomass and leaf chlorophyll content. UAS imagery was simulated by placing a Fuji IS-Pro UVIR digital camera at 3-m height looking nadir. An external UV-IR cut filter was used to acquire true-color images; an external red cut filter was used to obtain color-infrared-like images with bands at near-infrared, green, and blue wavelengths. Plot-scale Green Normalized Difference Vegetation Index was correlated with dry aboveground biomass (r = 0.58), whereas the Triangular Greenness Index (TGI) was not correlated with chlorophyll content. We used the SamplePoint program to select 100 pixels systematically; we visually identified the cover type and acquired the digital numbers. The number of rye pixels in each image was better correlated with biomass (r = 0.73), and the average TGI from only leaf pixels was negatively correlated with chlorophyll content (r = -0.72). Thus, better information for crop requirements may be obtained using very small pixel sizes, but new algorithms based on computer vision are needed for analysis. It may not be necessary to geospatially register large numbers of photographs with very small pixel sizes. Instead, images could be analyzed as single plots along field transects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 11. Enhancing Agricultural Geospatial Data Dissemination and Applications Using Geospatial Web Services

    Publication Year: 2014 , Page(s): 4539 - 4547
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1476 KB) |  | HTML iconHTML  

    There are many important publicly available agricultural geospatial data products for the agriculture-related research, applications, and educational outreach programs. The traditional data distribution method cannot fully meet users' on-demand geospatial data needs. This paper presents interoperable, standard-compliant Web services developed for geospatial data access, query, retrieval, statistics, mapping, and comparison. Those standard geospatial Web services can be integrated in scientific workflows to accomplish specific tasks or consumed over the Web to create value-added new geospatial application by users. In addition, this paper demonstrates, via real world use cases, applications of those services and potential impacts on facilitating geospatial Cropland Data Layer (CDL) retrieval, analysis, visualization, dissemination and integration in agricultural industry, government, research, and educational communities. This paper also shows that the geospatial Web service approach helps improve the reusability, interoperability, dissemination, and utilization of agricultural geospatial data. It allows for integrating multiple online applications and different geospatial data sources, and enables automated retrieving and delivery of agricultural geospatial information for decision-making support. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 12. Mountains Forest Fire Spread Simulator Based on Geo-Cellular Automaton Combined With Wang Zhengfei Velocity Model

    Publication Year: 2013 , Page(s): 1971 - 1987
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3937 KB) |  | HTML iconHTML  

    The aim of this paper is to propose a more practical mountain fire spread model for fire behavior prediction and management in Southwest forest area of China. These areas are covered mainly with spatial heterogeneous flammable forest and are characterized by undulating terrain and steep slopes. This model can produce more accurate fire propagation maps by combining CA (Cellular Automaton) framework with Wang Zhengfei fire physical velocity model in fine scale. Considering the inherent uncertainties of fire propagation, the model has been built on multi-dimension geophysical and environmental components and also sound knowledge of fire spread physical mechanism. Regarding small fuel patches as spatial homogenous cells, this approach makes it easier to generate higher level complex fire behavior maps from CA simple local rules and local behavior integrated with high resolution vegetation images, fine scale terrain maps and surface wind field. Because the model focuses primarily on the study of surface fire front propagation behavior, it attempts to simplify complex fuel modeling. Additionally, this Wang-Geophysical-CA model is able to analyze the time series spatial pattern of fire-front spread and model local behavior instead of the final fire spread pattern of the conventional approach. In this work, not only single influence verification tests have been made, but also simulation tests with multiple influences are carried out to demonstrate the capability of the model with fine scale vegetation maps, surface wind field, terrain, moisture content and man-made structures. Consequently, it is believable that the model predictions are in good agreement with experimental data for steady-state fire simulation. The proposed model helps to gain a greater understanding of the fire front spread local behavior and can quickly generate a sequence of complex fire front contours. It enables local managers to plan practical fire prevention activities in Southwest forest area of C- ina as well as improve fire management skills, and will enhance the effectiveness of fire fighting strategies. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 13. Optimizing Satellite Monitoring of Volcanic Areas Through GPUs and Multi-Core CPUs Image Processing: An OpenCL Case Study

    Publication Year: 2013 , Page(s): 2445 - 2452
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (505 KB) |  | HTML iconHTML  

    Satellite image processing algorithms often offer a very high degree of parallelism (e.g., pixel-by-pixel processing) that make them optimal candidates for execution on high-performance parallel computing hardware such as modern graphic processing units (GPUs) and multicore CPUs with vector processing capabilities. By using the OpenCL computing standard, a single implementation of a parallel algorithm can be deployed on a wide range of hardware platforms. However, achieving the best performance on each individual platform may still require a custom implementation. We show some possible approaches to the optimization of satellite image processing algorithms on a range of different platforms, discussing the implementation in OpenCL of the classic Brightness Temperature Difference ash-cloud detection algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 14. Efficient ELM-Based Techniques for the Classification of Hyperspectral Remote Sensing Images on Commodity GPUs

    Publication Year: 2015 , Article#: 2384133
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2091 KB)  

    Extreme learning machine (ELM) is an efficient learning algorithm that has been recently applied to hyperspectral image classification. In this paper, the first implementation of the ELM algorithm fully developed for graphical processing unit (GPU) is presented. ELM can be expressed in terms of matrix operations so as to take advantage of the single instruction multiple data (SIMD) computing paradigm of the GPU architecture. Additionally, several techniques like the use of ensembles, a spatial regularization algorithm, and a spectral???spatial classification scheme are applied and projected to GPU in order to improve the accuracy results of the ELM classifier. In the last case, the spatial processing is based on the segmentation of the hyperspectral image through a watershed transform. The experiments are performed on remote sensing data for land cover applications achieving competitive accuracy results compared to analogous support vector machine (SVM) strategies with significantly lower execution times. The best accuracy results are obtained with the spectral???spatial scheme based on applying watershed and a spatially regularized ELM. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 15. Unsupervised Change Detection in SAR Image Based on Gauss-Log Ratio Image Fusion and Compressed Projection

    Publication Year: 2014 , Article#: 2328344
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5970 KB) |  | HTML iconHTML  

    Multitemporal synthetic aperture radar (SAR) images have been successfully used for the detection of different types of terrain changes. SAR image change detection has recently become a challenge problem due to the existence of speckle and the complex mixture of terrain environment. This paper presents a novel unsupervised change detection method in SAR images based on image fusion strategy and compressed projection. First, a Gauss-log ratio operator is proposed to generate a difference image. In order to obtain a better difference map, image fusion strategy is applied using complementary information from Gauss-log ratio and log-ratio difference image. Second, nonsubsampled contourlet transform (NSCT) is used to reduce the noise of the fused difference image, and compressed projection is employed to extract feature for each pixel. The final change detection map is obtained by partitioning the feature vectors into “changed” and “unchanged” classes using simple k-means clustering. Experiment results show that the proposed method is effective for SAR image change detection in terms of shape preservation of the detected change portion and the numerical results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 16. Remote Sensing Image Super-Resolution Reconstruction Based on Nonlocal Pairwise Dictionaries and Double Regularization

    Publication Year: 2014 , Article#: 2328596
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2113 KB) |  | HTML iconHTML  

    A nonlocal pairwise dictionary learning (NPDL) model that includes an estimated dictionary and a residual dictionary is applied to remote sensing image super-resolution (SR) reconstruction in this paper. The dictionary pair is trained from some low-resolution (LR) remote sensing images to deal with the lack of high-resolution component in remote sensing images. The reconstructed image has been shown to retain the structural information of the given LR image itself. Moreover, the local and nonlocal (NL) priors are used for image SR to enhance robustness of the pairwise dictionary. Improved NL self-similarity and local kernel constraint regularization terms are introduced to the image optimization process. Using this, the photometric, geometric, and feature information of the given LR image can be taken into consideration to improve the quality of reconstruction. Simulation results show that the proposed algorithm can achieve better visual effects and the average peak signal-to-noise ratio (PSNR) is improved by approximately 0.5 db compared with the state-of-the-art image SR methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 17. Automatic Auroral Detection in Color All-Sky Camera Images

    Publication Year: 2014 , Article#: 2321433
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (935 KB) |  | HTML iconHTML  

    Every winter, the all-sky cameras (ASCs) in the MIRACLE network take images of the night sky at regular intervals of 10-20 s. This amounts to millions of images that not only need to be pruned, but there is also a need for efficient auroral activity detection techniques. In this paper, we describe a method for performing automated classification of ASC images into three mutually exclusive classes: aurora, no aurora, and cloudy. This not only reduces the amount of data to be processed, but also facilitates in building statistical models linking the magnetic fluctuations and auroral activity helping us to get a step closer to forecasting auroral activity. We experimented with different feature extraction techniques coupled with Support Vector Machines classification. Color variants of Scale Invariant Feature Transform (SIFT) features, specifically Opponent SIFT features, were found to perform better than other feature extraction techniques. With Opponent SIFT features, we were able to build a classification model with a cross-validation accuracy of 91%, which was further improved using temporal information and elimination of outliers which makes it accurate enough for operational data pruning purposes. Since the problem is essentially similar to scene detection, local point description features perform better than global- and texture-based feature descriptors. View full abstract»

    Open Access
  • 18. Application of Crop Model Data Assimilation With a Particle Filter for Estimating Regional Winter Wheat Yields

    Publication Year: 2014 , Page(s): 4422 - 4431
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1315 KB) |  | HTML iconHTML  

    To improve the performance of crop models for regional crop yield estimates, a particle filter (PF) was introduced to develop a data assimilation strategy using the Crop Environment Resource Synthesis (CERES)-Wheat model. Two experiments involving winter wheat yield estimations were conducted at a field plot and on a regional scale to test the feasibility of the PF-based data assimilation strategy and to analyze the effects of the PF parameters and spatiotemporal scales of assimilating observations on the performance of the crop model data assimilation. The significant improvements in the yield estimation suggest that PF-based crop model data assimilation is feasible. Winter wheat yields from the field plots were forecasted with a determination coefficient (R2) of 0.87, a root-mean-square error (RMSE) of 251 kg/ha, and a relative error (RE) of 2.95%. An acceptable yield at the county scale was estimated with a R2 of 0.998, a RMSE of 9734 t, and a RE of 4.29%. The optimal yield estimates may be highly dependent on the reasonable spatiotemporal resolution of assimilating observations. A configuration using a particle size of 50, LAI maps with a moderate spatial resolution (e.g., 1 km), and an assimilation interval of 20 d results in a reasonable tradeoff between accuracy and effectiveness in regional applications. View full abstract»

    Open Access
  • 19. Data Mining, A Promising Tool for Large-Area Cropland Mapping

    Publication Year: 2013 , Page(s): 2132 - 2138
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (668 KB) |  | HTML iconHTML  

    The northern fringe of sub-Saharan Africa is a region that is considered to be particularly vulnerable to climate variability and change, and it is a location in which food security remains a major challenge. To address these issues, it is essential to develop global data sets of the geographic distribution of agricultural land use. The objectives of this study were to test an original data mining approach for classifying and mapping the cropped land in West Africa using coarse-resolution imagery and to compare the classification results with those obtained from a classic ISODATA approach. The data mining approach is able to handle large volumes of data and is based on different descriptors (65) of the land use, including the spatial and temporal satellite-derived metrics of 12 MODIS NDVI 16-day composite images and the static attributes taken from field surveys. The classic ISODATA method showed that 68.3% of pixels from a SPOT reference map were correctly classified in three validation sites versus 57.8% for the data mining approach. Validation by field observations showed equivalent results for both methods with an F-score of 0.72. The results of this study demonstrated the relevance of the use of data-mining tools for large-area monitoring. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 20. Recent Developments in High Performance Computing for Remote Sensing: A Review

    Publication Year: 2011 , Page(s): 508 - 527
    Cited by:  Papers (42)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1665 KB) |  | HTML iconHTML  

    Remote sensing data have become very widespread in recent years, and the exploitation of this technology has gone from developments mainly conducted by government intelligence agencies to those carried out by general users and companies. There is a great deal more to remote sensing data than meets the eye, and extracting that information turns out to be a major computational challenge. For this purpose, high performance computing (HPC) infrastructure such as clusters, distributed networks or specialized hardware devices provide important architectural developments to accelerate the computations related with information extraction in remote sensing. In this paper, we review recent advances in HPC applied to remote sensing problems; in particular, the HPC-based paradigms included in this review comprise multiprocessor systems, large-scale and heterogeneous networks of computers, grid and cloud computing environments, and hardware systems such as field programmable gate arrays (FPGAs) and graphics processing units (GPUs). Combined, these parts deliver a snapshot of the state-of-the-art and most recent developments in those areas, and offer a thoughtful perspective of the potential and emerging challenges of applying HPC paradigms to remote sensing problems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 21. A Nonlocal Weighted Joint Sparse Representation Classification Method for Hyperspectral Imagery

    Publication Year: 2014 , Page(s): 2056 - 2065
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2125 KB) |  | HTML iconHTML  

    As a powerful and promising statistical signal modeling technique, sparse representation has been widely used in various image processing and analysis fields. For hyperspectral image classification, previous studies have shown the effectiveness of the sparsity-based classification methods. In this paper, we propose a nonlocal weighted joint sparse representation classification (NLW-JSRC) method to improve the hyperspectral image classification result. In the joint sparsity model (JSM), different weights are utilized for different neighboring pixels around the central test pixel. The weight of one specific neighboring pixel is determined by the structural similarity between the neighboring pixel and the central test pixel, which is referred to as a nonlocal weighting scheme. In this paper, the simultaneous orthogonal matching pursuit technique is used to solve the nonlocal weighted joint sparsity model (NLW-JSM). The proposed classification algorithm was tested on three hyperspectral images. The experimental results suggest that the proposed algorithm performs better than the other sparsity-based algorithms and the classical support vector machine hyperspectral classifier. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 22. A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results

    Publication Year: 2013 , Page(s): 2102 - 2131
    Cited by:  Papers (4)  |  Patents (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (5115 KB) |  | HTML iconHTML  

    A general framework for processing high and very-high resolution imagery in support of a Global Human Settlement Layer (GHSL) is presented together with a discussion on the results of the first operational test of the production workflow. The test involved the mapping of 24.3 million km2 of the Earth surface spread in four continents, corresponding to an estimated population of 1.3 billion people in 2010. The resolution of the input image data ranges from 0.5 to 10 meters, collected by a heterogeneous set of platforms including satellite SPOT (2 and 5), CBERS 2B, RapidEye (2 and 4), WorldView (1 and 2), GeoEye 1, QuickBird 2, Ikonos 2, and airborne sensors. Several imaging modes were tested including panchromatic, multispectral and pan-sharpened images. A new fully automatic image information extraction, generalization and mosaic workflow is presented that is based on multiscale textural and morphological image features extraction. New image feature compression and optimization are introduced, together with new learning and classification techniques allowing for the processing of HR/VHR image data using low-resolution thematic layers as reference. A new systematic approach for quality control and validation allowing global spatial and thematic consistency checking is proposed and applied. The quality of the results are discussed by sensor, band, resolution, and eco-regions. Critical points, lessons learned and next steps are highlighted. View full abstract»

    Open Access
  • 23. Advanced Signal Processing for Vital Sign Extraction With Applications in UWB Radar Detection of Trapped Victims in Complex Environments

    Publication Year: 2014 , Page(s): 783 - 791
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1931 KB) |  | HTML iconHTML  

    Ultra-wideband (UWB) radar plays an important role in search and rescue at disaster relief sites. Identifying vital signs and locating buried survivors are two important research contents in this field. In general, it is hard to identify a human's vital signs (breathing and heartbeat) in complex environments due to the low signal-to-noise ratio of the vital sign in radar signals. In this paper, advanced signal-processing approaches are used to identify and to extract human vital signs in complex environments. First, we apply Curvelet transform to remove the source-receiver direct coupling wave and background clutters. Next, singular value decomposition is used to de-noise in the life signals. Finally, the results are presented based on FFT and Hilbert-Huang transform to separate and to extract human vital sign frequencies, as well as the micro-Doppler shift characteristics. The proposed processing approach is first tested by a set of synthetic data generated by FDTD simulation for UWB radar detection of two trapped victims under debris at an earthquake site of collapsed buildings. Then, it is validated by laboratory experiments data. The results demonstrate that the combination of UWB radar as the hardware and advanced signal-processing algorithms as the software has potential for efficient vital sign detection and location in search and rescue for trapped victims in complex environment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 24. Urban Land Cover Classification With Airborne Hyperspectral Data: What Features to Use?

    Publication Year: 2014 , Page(s): 3998 - 4009
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1494 KB) |  | HTML iconHTML  

    This paper investigates the potential effects of spectral, shape, textural, and height information and their combinations on the classification of urban areas using airborne hyperspectral data. Based on analysis of the spectral, shape, textural, and height characteristics of urban land covers, the first ten spectral principal components, eight shape components, one height component, and seven textural components were selected to examine their performance on the classification accuracy. Correlation analysis was conducted to exclude correlated components. A support vector machine (SVM) was employed to determine the significant components affecting the urban hyperspectral classification through comparison of the classification accuracy. Different combinations of these components were then tested to estimate their contributes. The classification results showed that all these components contribute to the result of urban land cover classification, but different land cover classes benefit from the inclusion of different components. The experiment further revealed the effect of significant components on the classification of urban land cover in terms of area, convexity, elongation, form factor, rectangular fit, roundness, textual factors, and mean relative height. It is suggested that the inclusion of shape, texture, and height, together with the spectral components, significantly improved the classification accuracy of urban land cover. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 25. Compression of Hyperspectral Images Containing a Subpixel Target

    Publication Year: 2014 , Page(s): 2246 - 2255
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1985 KB) |  | HTML iconHTML  

    Hyperspectral (HS) image sensors measure the reflectance of each pixel at a large number of narrow spectral bands, creating a three-dimensional representation of the captured scene. The HS image (HSI) consumes a great amount of storage space and transmission time. Hence, it would be desirable to reduce the image representation to the extent possible using a compression method appropriate to the usage and processing of the image. Many compression methods have been proposed aiming at different applications and fields. This research focuses on the lossy compression of images that contain subpixel targets. This target type requires minimum compression loss over the spatial dimension in order to preserve the target, and the maximum possible spectral compression that would still enable target detection. For this target type, we propose the PCA-DCT (principle component analysis followed by the discrete cosine transform) compression method. It combines the PCA's ability to extract the background from a small number of components, with the individual spectral compression of each pixel of the residual image, obtained by excluding the background from the HSI, using quantized DCT coefficients. The compression method is kept simple for fast processing and implementation, and considers lossy compression only on the spectral axis. The spectral compression achieves a compression ratio of over 20. The popular Reed-Xiaoli (RX) algorithm and the improved quasi-local RX (RXQLC) are used as target detection methods. The detection performance is evaluated using receiver operating characteristics (ROC) curve generation. The proposed compression method achieves maintained and enhanced detection performance, compared to the detection performance of the original image, mainly due to its inherent smoothing and noise reduction effects. Our proposed method is also compared with two other compression methods: PCA-ICA (independent component analysis) and band decimation (BandDec), yi- lding superior results for high compression rates. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 26. RADARSAT-2 Polarimetric SAR Response to Crop Biomass for Agricultural Production Monitoring

    Publication Year: 2014 , Article#: 2322311
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1365 KB) |  | HTML iconHTML  

    Agricultural production monitoring plays a key role in a variety of economic and environmental practices including crop yield forecasting, identifying risk of disease and application of chemicals. Remote sensing has the potential to provide accurate crop condition information across large areas and has the ability to deliver information products in a timely within-season manner. Synthetic aperture radar (SAR) frequencies are unaffected by most atmospheric conditions, making use of this technology of interest to crop monitoring. In this study, RADARSAT-2 polarimetric SAR responses of 21 parameters are compared with dry biomass of canola, corn, soybean, and spring wheat crops over a 6-week period for a site in western Canada. Dry biomass was targeted as this variable is a strong predictor of crop productivity. During the period of biomass accumulation, significant correlations with dry biomass were observed for most SAR parameters, for corn, canola, and soybeans. These findings are of interest as they could be used to target fungicide applications (canola) and to determine silage yields and resistance to disease (corn). For spring wheat, linear cross polarization and circular cross polarization backscatter, volume scattering and pedestal height were able to detect when wheat entered the milking stage which could prove useful as an indicator for the timing of spring wheat harvest. This study demonstrates that polarimetric SAR responds to accumulation of dry biomass, but as well that several radar parameters can uniquely identify changes in crop structure and phenology. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 27. Google Fusion Tables for Managing Soil Moisture Sensor Observations

    Publication Year: 2014 , Article#: 2353621
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1230 KB) |  | HTML iconHTML  

    Soil moisture plays a significant role in both water and energy cycles. It is important to manage and analyze in situ sensor observations of soil moisture due to its impacts on agricultural and hydrological processes. Google Fusion Tables (GFT) is a cloud computing database that provides a service on the Web for data management and integration. Using GFT for managing soil moisture sensor observations, it is possible to take advantages of GFT for collaborative management, on-the-fly visualization, and flexible integration and analysis. The Open Geospatial Consortium (OGC) sensor observation service (SOS) can provide real-time or near-real-time observations in an interoperable way. Combing SOS and GFT together can take the best of both. The paper investigates how GFT could be employed for managing, visualizing, and analyzing soil moisture sensor observations. It describes the design and implementation of a cloud-based SOS for managing soil moisture data using cloud computing databases. By storing sensor observations in GFT, the SOS service is scalable, and observations can be visualized and analyzed on demand. Challenges and approaches on the integration of GFT and SOS are discussed. A prototype service on sharing and managing soil moisture sensor observations is developed to demonstrate the applicability of the approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 28. Progress in Hyperspectral Remote Sensing Science and Technology in China Over the Past Three Decades

    Publication Year: 2014 , Page(s): 70 - 91
    Cited by:  Papers (2)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (3312 KB) |  | HTML iconHTML  

    This paper reviews progress in hyperspectral remote sensing (HRS) in China, focusing on the past three decades. China has made great achievements since starting in this promising field in the early 1980s. A series of advanced hyperspectral imaging systems ranging from ground to airborne and satellite platforms have been designed, built, and operated. These include the field imaging spectrometer system (FISS), the Modular Airborne Imaging Spectrometer (MAIS), and the Chang'E-I Interferometer Spectrometer (IIM). In addition to developing sensors, Chinese scientists have proposed various novel image processing techniques. Applications of hyperspectral imaging in China have been also performed including mineral exploration in the Qilian Mountains and oil exploration in Xinjiang province. To promote the development of HRS, many generic and professional software tools have been developed. These tools such as the Hyperspectral Image Processing and Analysis System (HIPAS) incorporate a number of special algorithms and features designed to take advantage of the wealth of information contained in HRS data, allowing them to meet the demands of both common users and researchers in the scientific community. View full abstract»

    Open Access
  • 29. A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification

    Publication Year: 2014 , Page(s): 317 - 326
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1923 KB) |  | HTML iconHTML  

    Hyperspectral imaging fully portrays materials through numerous and contiguous spectral bands. It is a very useful technique in various fields, including astronomy, medicine, food safety, forensics, and target detection. However, hyperspectral images include redundant measurements, and most classification studies encountered the Hughes phenomenon. Finding a small subset of effective features to model the characteristics of classes represented in the data for classification is a critical preprocessing step required to render a classifier effective in hyperspectral image classification. In our previous work, an automatic method for selecting the radial basis function (RBF) parameter (i.e., σ) for a support vector machine (SVM) was proposed. A criterion that contains the between-class and within-class information was proposed to measure the separability of the feature space with respect to the RBF kernel. Thereafter, the optimal RBF kernel parameter was obtained by optimizing the criterion. This study proposes a kernel-based feature selection method with a criterion that is an integration of the previous work and the linear combination of features. In this new method, two properties can be achieved according to the magnitudes of the coefficients being calculated: the small subset of features and the ranking of features. Experimental results on both one simulated dataset and two hyperspectral images (the Indian Pine Site dataset and the Pavia University dataset) show that the proposed method improves the classification performance of the SVM. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 30. Regional Grain Yield Response to Climate Change in China: A Statistic Modeling Approach

    Publication Year: 2014 , Article#: 2357584
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (851 KB) |  | HTML iconHTML  

    China is the world's most populous country with only 7% of the world's arable land. Accurate assessment of the effect that future climate change may pose on grain production is essential to the sustainability of agriculture. Model variations plus uncertainties in the future climate change scenarios create a big challenge for such evaluation. In this work, we developed the statistical models for six different regions in China, using the historical yield data between 1981 and 2010 from the National Bureau of Statistics combined with meteorological station observations and analyzed the impact of climate variation (i.e., temperature and precipitation changes) on the grain yields into the 2030s, based on 28 ensemble climate predictions from six state-of-the-art Coupled Model Intercomparison Project Phase 5 (CMIP5) model outputs. Our results indicate that the four crops (i.e., rice, maize, wheat, and soybean) respond similarly to the climate variation in different regions of China, with the sensitivity to warming increasing from north to south and from inner land to coast regions. In addition, the yields of all the four crops in East and Central-South China are also positively correlated with precipitation change. Future projections with a medium greenhouse gas mitigation scenario (RCP4.5) showed that the yield of the four crops in six regions of China would increase ranging from 0.02 to 1.19 hundred ton/ha, in 2030s with respect to the 2000s. Nevertheless, adaptive implementations such as appropriately improve the irrigation infrastructure in East and Central-South China could mitigate the adverse impact from future climate change. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 31. An Overview of Background Modeling for Detection of Targets and Anomalies in Hyperspectral Remotely Sensed Imagery

    Publication Year: 2014 , Page(s): 2317 - 2336
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (2917 KB) |  | HTML iconHTML  

    This paper reviews well-known classic algorithms and more recent experimental approaches for distinguishing the weak signal of a target (either known or anomalous) from the cluttered background of a hyperspectral image. Making this distinction requires characterization of the targets and characterization of the backgrounds, and our emphasis in this review is on the backgrounds. We describe a variety of background modeling strategies-Gaussian and non-Gaussian, global and local, generative and discriminative, parametric and nonparametric, spectral and spatio-spectral-in the context of how they relate to the target and anomaly detection problems. We discuss the major issues addressed by these algorithms, and some of the tradeoffs made in choosing an effective algorithm for a given detection application. We identify connections among these algorithms and point out directions where innovative modeling strategies may be developed into detection algorithms that are more sensitive and reliable. View full abstract»

    Open Access
  • 32. SAR Image Classification Through Information-Theoretic Textural Features, MRF Segmentation, and Object-Oriented Learning Vector Quantization

    Publication Year: 2014 , Page(s): 1116 - 1126
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2552 KB) |  | HTML iconHTML  

    Segmentation of optical images may be obtained through algorithms based on image prior models that exploit the spatial dependencies of land covers. In synthetic aperture radar (SAR) images, speckle conceals such spatial dependencies and segmentation algorithms suitable for optical images may become ineffective. Textural features may be used to emphasize spatial dependencies in the data and hence to improve segmentation. Once segmentation has been accomplished, a number of shapes is available. In this paper, the problem is tackled through the joint use of information-theoretic (IT) SAR features, of a segmentation algorithm based on tree structured Markov random fields (TS-MRFs), and of object-oriented classification achieved through learning vector quantization (LVQ). The proposed system works with one or more coregistered images, not necessarily all SAR, and one or more spatial maps of pixel features derived from each input image. A unique partition into connected regions, or segments, is achieved from the plurality of input channels, either images or feature maps. From each segment, representing a shape, geometric, radiometric, and textural parameters are extracted and fed to an LVQ classifier, trained through a partial reference ground truth (GT) of the scene. Classification results on a textured SAR image of a city and its surroundings validate the proposed object-oriented approach. Good performances can be achieved with small sizes of training sets, but they can be improved by using a decision fusion through majority voting (MV) of the outcomes of several experiments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 33. Cloud Computing Enabled Web Processing Service for Earth Observation Data Processing

    Publication Year: 2012 , Page(s): 1637 - 1649
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2975 KB) |  | HTML iconHTML  

    The OpenGIS Web Processing Service (WPS) can process both simple and complex geospatial tasks including Earth Observation tasks. As the requirements of Earth Observation data, algorithms, calculation models, and daily life become increasingly complicated; WPS needs to provide high-performance service-oriented computing capability. This paper proposes a cloud computing enabled WPS framework for Earth Observation data processing. It consists of a client layer and a WPS layer, which further consists of a WPS server layer and a cloud computing layer. The cloud computing environment is based on the open-source software Apache Hadoop. The three layers of the proposed cloud computing enabled WPS are outlined, followed by a workflow that processes a user's task using these three layers. Then technological implementation details are explained. An experiment processing Moderate Resolution Imaging Spectroradiometer (MODIS) data shows that WPS can be enabled in a cloud computing environment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 34. Estimating Vegetation Fraction Using Hyperspectral Pixel Unmixing Method: A Case Study of a Karst Area in China

    Publication Year: 2014 , Article#: 2361253
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (999 KB) |  | HTML iconHTML  

    The rocky desertification is one of three major ecological problems in the karst areas in southwestern China. Vegetation fraction, bare soil, and bare rock are main typical surface characteristics obtained from remote sensing data when evaluating rocky desertification in these areas. How to estimate vegetation coverage more precisely is a challenging topic because the issues of complex surface coverage, highly spatial heterogeneity, and mixed-pixels should be addressed. Hyperspectral pixel unmixing is a better approach to solve these issues. In this paper, the Hyperion hyperspectral remotely sensed image is used as the source data, vegetation, soil, and rock are selected as three typical land cover features, and the pixel purity index (PPI) is utilized to distill the endmember spectral. Then, the pixel unmixing methods, including matched filtering (MF) and mixture tuned matched filtering (MTMF) are adopted to estimate vegetation coverage of the studied karst area, respectively. The results show that: 1) the maximum deviation between the ground-surveyed vegetation fraction and the MTMF-inversed one is acceptable, and so are the deterministic coefficient and the root mean square error (RMSE); 2) the MTMF-inversed results are more accurate than the ones inversed from the MF method and the MTMF-inversed vegetation coverage can be used to estimate the actual vegetation fraction. The results also demonstrate the applicability of the MTMF method in evaluating vegetation fraction in the karst regions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 35. Efficient and Effective Hierarchical Feature Propagation

    Publication Year: 2014 , Article#: 2341175
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1822 KB) |  | HTML iconHTML  

    Many methods have been recently proposed to deal with the large amount of data provided by the new remote sensing technologies. Several of those methods rely on the use of segmented regions. However, a common issue in region-based applications is the definition of the appropriate representation scale of the data, a problem usually addressed by exploiting multiple scales of segmentation. The use of multiple scales, however, raises new challenges related to the definition of effective and efficient mechanisms for extracting features. In this paper, we address the problem of extracting features from a hierarchy by proposing two approaches that exploit the existing relationships among regions at different scales. The H-Propagation propagates any histogram-based low-level descriptors. The bag-of-visual-word (BoW)-Propagation approach uses the BoWs model to propagate features along multiple scales. The proposed methods are very efficient, as features need to be extracted only at the base of the hierarchy and yield comparable results to low-level extraction approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 36. An Online Coupled Dictionary Learning Approach for Remote Sensing Image Fusion

    Publication Year: 2014 , Page(s): 1284 - 1294
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2479 KB) |  | HTML iconHTML  

    Most earth observation satellites, such as IKONOS, QuickBird, GeoEye, and WorldView-2, provide a high spatial resolution (HR) panchromatic (Pan) image and a multispectral (MS) image at a lower spatial resolution (LR). Image fusion is an effective way to acquire the HR MS images that are widely used in various applications. In this paper, we propose an online coupled dictionary learning (OCDL) approach for image fusion, in which a superposition strategy is applied to construct the coupled dictionaries. The constructed coupled dictionaries are further developed via an iterative update to ensure that the HR MS image patch can be almost identically reconstructed by multiplying the HR dictionary and the sparse coefficient vector, which is solved by sparsely representing its counterpart LR MS image patch over the LR dictionary. The fusion results from IKONOS and WorldView-2 data show that the proposed fusion method is competitive or even superior to the other state-of-the-art fusion methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 37. A Robust Nonlocal Fuzzy Clustering Algorithm With Between-Cluster Separation Measure for SAR Image Segmentation

    Publication Year: 2014 , Page(s): 4929 - 4936
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1672 KB) |  | HTML iconHTML  

    Fuzzy c-means (FCM) algorithm has been widely used in image segmentation, and there have been many improved algorithms proposed. But when dealing with synthetic aperture radar (SAR) images, they may not give satisfactory segmentation results because of speckle noise. In order to segment SAR image effectively, a robust Fuzzy clustering algorithm is proposed, called nonlocal fuzzy clustering algorithm with between-cluster separation measure (NS_FCM). In NS_FCM, to reduce the effects of the noise, we incorporate the nonlocal spatial information obtained using an improved nonlocal mean method, which adopts adaptive binary weighted distance measure and adaptive filtering degree parameter. In addition, we introduce a fuzzy between-cluster variation term into the objective function. Based on this, while minimizing the objective function, we can maximize the within-cluster compactness measure and the between-cluster separation measure of the partition simultaneously. Besides, by regulating the parameter of the fuzzy between-cluster variation term, we can adjust the distance between the clustering centers flexibly. This makes NS_FCM more effective to the images, which have some close classes in feature space. Experiments on synthetic and real SAR images show that the proposed method behaves well in SAR image segmentation performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 38. Non-Local Sparse Unmixing for Hyperspectral Remote Sensing Imagery

    Publication Year: 2014 , Page(s): 1889 - 1909
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6041 KB) |  | HTML iconHTML  

    Sparse unmixing is a promising approach that acts as a semi-supervised unmixing strategy by assuming that the observed image signatures can be expressed in the form of linear combinations of a number of pure spectral signatures that are known in advance. However, conventional sparse unmixing involves finding the optimal subset of signatures for the observed data in a very large standard spectral library, without considering the spatial information. In this paper, a new sparse unmixing algorithm based on non-local means, namely non-local sparse unmixing (NLSU), is proposed to perform the unmixing task for hyperspectral remote sensing imagery. In NLSU, the non-local means method, as a regularizer for sparse unmixing, is used to exploit the similar patterns and structures in the abundance image. The NLSU algorithm based on the sparse spectral unmixing model can improve the spectral unmixing accuracy by incorporating the non-local spatial information by means of a weighting average for all the pixels in the abundance image. Five experiments with three simulated and two real hyperspectral images were performed to evaluate the performance of the proposed algorithm in comparison to the previous sparse unmixing methods: sparse unmixing via variable splitting and augmented Lagrangian (SUnSAL) and sparse unmixing via variable splitting augmented Lagrangian and total variation (SUnSAL-TV). The experimental results demonstrate that NLSU outperforms the other algorithms, with a better spectral unmixing accuracy, and is an effective spectral unmixing algorithm for hyperspectral remote sensing imagery. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 39. Regions of Interest Detection in Panchromatic Remote Sensing Images Based on Multiscale Feature Fusion

    Publication Year: 2014 , Article#: 2319736
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2195 KB) |  | HTML iconHTML  

    A global searching solution was often employed in traditional prior-knowledge-based regions of interest (ROIs) detection methods for processing high-resolution remote sensing images, which results in prohibitively complex computing. To solve this problem, this study proposes a faster and more efficient ROI detection algorithm based on multiscale feature fusion, wherein the input image is processed along two feature channels: intensity and orientation. The multiscale spectrum residuals method is proposed to compute intensity saliency. The interpolating biorthogonal integer wavelet transform (IB-IWT) is used to extract orientation features, and the orientation saliency is obtained with thresholding and filtering. A weighted across-scale fusion method is proposed to combine conspicuity maps at different scales into one map while retaining salient regions at different scales. The experimental results reveal that the new algorithm is computationally efficient and provides more visually accurate detection results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 40. Endmember Extraction Guided by Anomalies and Homogeneous Regions for Hyperspectral Images

    Publication Year: 2014 , Article#: 2330364
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2046 KB) |  | HTML iconHTML  

    Endmember extraction is the process of selecting pure spectral signatures of materials from hyperspectral data. Most of the endmember extraction methods in the literature use only the spectral information, and disregard the spatial composition of the image. Spatial-spectral preprocessing methods, motivated by the assumption that endmembers are more likely to be located in homogenous regions, can increase the performance of endmember extraction by directing the extraction process to homogenous regions. However, such an approach generally results in a failure of extracting anomalous or scarce endmembers, which can be important in practical applications, e.g., to extract endmembers of materials such as landmines, rare minerals, or stressed crops. Although anomaly detection can be applied in parallel to endmember extraction, the process of endmember extraction and unmixing provides a summary of the data, which is important for concepts such as data scanning and compression, and disregarding anomalous endmembers in such a summary or compression of big data may result in undesired consequences for many application fields. In this paper, an approach that guides the endmember extraction process to spatially homogenous regions instead of transition areas, while also extracting anomalous pixel vectors as endmembers, is proposed. The proposed approach can be used with any spectral-based endmember extraction method. The experimental results validate the approach for both synthetic and real hyperspectral images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 41. A Novel Compressive Sensing Algorithm for SAR Imaging

    Publication Year: 2014 , Page(s): 708 - 720
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3707 KB) |  | HTML iconHTML  

    A novel compressive sensing (CS) algorithm for synthetic aperture radar (SAR) imaging is proposed which is called as the two-dimensional double CS algorithm (2-D-DCSA). We first derive the imaging operator for SAR, which is named as the chirp-scaling operator (CSO), from the chirp-scaling algorithm (CSA), then we show its inverse is a linear map, which transforms the SAR image to the received baseband radar signal. We show that the SAR image can be reconstructed simultaneously in the range and azimuth directions from a small number of the raw data. The proposed algorithm can handle large-scale data because both the CSO and its inverse allow fast matrix-vector multiplications. Both the simulated and real data are processed to test the algorithm and the results show that the 2-D-DCSA can be applied to reconstructing the SAR images effectively with much less data than regularly required. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 42. Building Change Detection From Multitemporal High-Resolution Remotely Sensed Images Based on a Morphological Building Index

    Publication Year: 2014 , Page(s): 105 - 115
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2809 KB) |  | HTML iconHTML  

    In this study, urban building change detection is investigated, considering that buildings are one of the most dynamic structures in urban areas. To this aim, a novel building change detection approach for multitemporal high-resolution images is proposed based on a recently developed morphological building index (MBI), which is able to automatically indicate the presence of buildings from high-resolution images. In the MBI-based change detection framework, the changed building information is decomposed into MBI, spectral, and shape conditions. A variation of the MBI is a basic condition for the indication of changed buildings. Besides, the spectral information is used as a mask since the change of buildings is primarily related to the spectral variation, and the shape condition is then used as a post-filter to remove irregular structures such as noise and road-like narrow objects. The change detection framework is carried out based on a threshold-based processing at both the feature and decision levels. The advantages of the proposed method are that it does not need any training samples and it is capable of reducing human labor, considering the fact that the current building change detection methods are totally reliant on visual interpretation. The proposed method is evaluated with a QuickBird dataset from 2002 and 2005 covering Hongshan District of Wuhan City, China. The experiments show that the proposed change detection algorithms can achieve satisfactory correctness rates (over 80%) with a low level of total errors (less than 10%), and give better results than the supervised change detection using the support vector machine (SVM). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 43. Quality Assessment of Despeckled SAR Images

    Publication Year: 2014 , Page(s): 691 - 707
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (4454 KB) |  | HTML iconHTML  

    In this paper, a novel method for the quality assessment of despeckled SAR images is proposed. This method is based on the observation that the perceived quality of despeckled SAR images is not always appropriately described by classical statistical and deterministic parameters that are proposed in the literature. Various evaluations are performed here. A preliminary visual qualitative evaluation is taken as a reference for the subsequent quantitative assessment. Then, a revised statistical analysis that can solve some of the drawbacks of previous methods is proposed; however, the statistical approach still has certain drawbacks. To address this problem, a new frequency analysis approach is first proposed, together with a definition of the appropriate indexes. In this way, it is possible to select the best filter in terms of noise reduction, edge and texture preservation, while limiting the effect of introduced distortions. While statistical analysis is widely used in the literature, frequency analysis has never been presented for this aim, especially for non-linear filters. We prove that frequency analysis can robustly identify the best filter, taking perceptual considerations into account, even when statistical analysis fails. Despeckling methods based on anisotropic diffusion algorithms are used for a comparison, but the proposed analysis can be applied to any filtering method. Experiments are presented with SAR images from the Italian Cosmo/Skymed constellation. Both Stripmap and Spotlight acquisitions have been evaluated, and to prove the validity of the proposed method with respect to different spatial resolutions and different classes of interest, various classes are considered. View full abstract»

    Open Access
  • 44. {{\rm E}^{2}}{\rm LMs} : Ensemble Extreme Learning Machines for Hyperspectral Image Classification

    Publication Year: 2014 , Page(s): 1060 - 1069
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2893 KB) |  | HTML iconHTML  

    Extreme learning machine (ELM) has attracted attentions in pattern recognition field due to its remarkable advantages such as fast operation, straightforward solution, and strong generalization. However, the performance of ELM for high-dimensional data, such as hyperspectral image, is still an open problem. Therefore, in this paper, we introduce ELM for hyperspectral image classification. Furthermore, in order to overcome the drawbacks of ELM caused by the randomness of input weights and bias, two new algorithms of ensemble extreme learning machines (Bagging-based and AdaBoost-based ELMs) are proposed for the classification task. In order to illustrate the performance of the proposed algorithms, support vector machines (SVMs) are used for evaluation and comparison. Experimental results with real hyperspectral images collected by reflective optics spectrographic image system (ROSIS) and airborne visible/infrared imaging spectrometer (AVIRIS) indicate that the proposed ensemble algorithms produce excellent classification performance in different scenarios with respect to spectral and spectral-spatial feature sets. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 45. River Delineation from Remotely Sensed Imagery Using a Multi-Scale Classification Approach

    Publication Year: 2014 , Page(s): 4726 - 4737
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2614 KB) |  | HTML iconHTML  

    River delineation is an initial yet critical step in river studies. Although the analysis of satellite images shows great potential in river delineation, only a few approaches have been developed. These methods usually focus on rivers at mono-scale and may ignore the large variations in river size. In particular, they may fail to capture the small rivers in the imagery. This paper presents a novel automated multi-scale procedure for delineating complete river networks. This method classifies the large and small rivers separately and combines the two classified results to generate the final delineated river networks. First, a modified normalized difference water index (MNDWI) is adapted to enhance the spectral contrast between open water and land surfaces. Second, a simple OTSU classification is used to delineate the large rivers. Next, a top-hat transformation and multi-scale matched filters are used to enhance the small linear rivers. Then, the OTSU classification is conducted again to delineate the small linear rivers, in concert with a multi-points fast marching method to rejoin the resulting river segments. Finally, the complete river networks are delineated by combining the small and large rivers. A comparison of this procedure with manual digitization when applied to two Landsat-5 TM images demonstrates the former procedure's value in delineating rivers. It achieves accurate results and outperforms the other three alternative approaches (large river classification, maximum likelihood classifier, and support vector machine classifier) in accuracy, true positive rate, and Kappa coefficient, while also yielding a comparable false positive rate. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 46. Information Content of Very-High-Resolution SAR Images: Semantics, Geospatial Context, and Ontologies

    Publication Year: 2014 , Article#: 2363595
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2980 KB)  

    Currently, the amount of collected Earth Observation (EO) data is increasing considerably with a rate of several Terabytes of data per day. As a consequence of this increasing data volume, new concepts for exploration and information retrieval are urgently needed. To this end, we propose to explore satellite image data via an image information mining (IIM) approach in which the main steps are feature extraction, classification, semantic annotation, and interactive query processing. This leads to a new process chain and a robust taxonomy for the retrieved categories capitalizing on human interaction and judgment. We concentrated on land cover categories that can be retrieved from high-resolution synthetic aperture radar (SAR) images of the spaceborne TerraSAR-X instrument, where we annotated different urban areas all over the world and defined a taxonomy element for each prevailing surface cover category. The annotation resulted from a test dataset comprising more than 100 scenes covering diverse areas of Africa, Asia, Europe, the Middle East, and North and South America. The scenes were grouped into several collections with similar source areas and each collection was processed separately in order to discern regional characteristics. In the first processing step, each scene was tiled into patches. Then the features were extracted from each patch by a Gabor filter bank and a support vector machine with relevance feedback classifying the feature sets into user-oriented land cover categories. Finally, the categories were semantically annotated using Google Earth for ground truthing. The annotation followed a multilevel approach that allowed the fusion of information being visible on different resolution levels. The novelty of this paper lies in the fact that a semantic annotation was performed with a large number of high-resolution radar images that allowed the definition of more than 850 surface cover categories. This opens the way toward an automated identification - nd classification of urban areas, infrastructure (e.g., airports), geographic objects (e.g., mountains), industrial installations, military compounds, vegetation, and agriculture. Applications that may result from this work can be a semantic catalog of urban images to be used in crisis situations or after a disaster. In addition, the proposed taxonomies can become a basis for building a semantic catalog of satellite images. Finally, we defined four powerful types of high-level queries. Querying on such high levels provides new opportunities for users to search an image database for specific parameters or semantic relationships. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 47. Classification of Australian Native Forest Species Using Hyperspectral Remote Sensing and Machine-Learning Classification Algorithms

    Publication Year: 2014 , Page(s): 2481 - 2489
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1032 KB) |  | HTML iconHTML  

    Mapping forest species is highly relevant for many ecological and forestry applications. In Australia, the classification of native forest species using remote sensing data remains a particular challenge since there are many eucalyptus species that belong to the same genus and, thus, exhibit similar biophysical characteristics. This study assessed the potential of using hyperspectral remote sensing data and state-of-the-art machine-learning classification algorithms to classify Australian forest species at the leaf, canopy and community levels in Beecroft Peninsula, NSW, Australia. Spectral reflectance was acquired from an ASD spectrometer and airborne Hymap imagery for seven native forest species over an Australian eucalyptus forest. Three machine-learning classification algorithms: Support Vector Machine (SVM), AdaBoost and Random Forest (RF) were applied to classify the species. A comparative study was carried out between machine-learning classification algorithms and Linear Discriminant Analysis (LDA). The classification results show that all machine-leaning classification algorithms significantly improve the results produced by LDA. At the leaf level, RF achieved the best classification accuracy (94.7%), and SVM outperformed the other algorithms at both the canopy (84.5%) and community levels (75.5%). This study demonstrates that hyperspectral remote sensing and machine-learning classification has substantial potential for the classification of Australian native forest species. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 48. Estimation of Soil Moisture in Mountain Areas Using SVR Technique Applied to Multiscale Active Radar Images at C-Band

    Publication Year: 2015 , Article#: 2378795
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3156 KB) |  | HTML iconHTML  

    This paper presents an approach for retrieval of soil moisture content (SMC) from different satellite sensors with a focus on mountain areas. The novelties of the paper are: the extension of an already developed method to coarse resolution data (150 m) in mountain environment with high land heterogeneity, with only VV polarization and the proper selection of input features. During the result analysis, several algorithm characteristics were clearly identified: 1) the performances showed to be strongly related to input features such as topography and vegetation indices; 2) the algorithm needs a training phase; 3) the averaging window needs to be proper selected to take into account both the speckle noise and the characteristics of the area under investigation; and 4) the algorithm, being data driven, can be considered as site dependent. The experimental analysis is carried out on images acquired over the Südtirol/Alto Adige Province in Italy during 2010–2011 from the RADARSAT2 and Envisat ASAR in Wide Swath mode. SMC maps were compared with spatially distributed ground measurements, resulting in a root mean squared error (RMSE) value ranging from 0.045 to $0.07;{{rm m}^3}/{{rm m}^3}$. Concerning the multiscale analysis, the results indicated that RADARSAT2 maps are able to detect the spatial heterogeneity and soil moisture dynamics at local scale, while ASAR WS SMC maps are able to identify mainly the two main classes of pasture and meadows. When these estimates are compared with SMC values from meteorological stations a RMSE value of $0.10;{{rm m}^3}/{{rm m}^3}$ for both satellites indicated a reduced capability to follow the temporal dynamics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 49. A Review of Nonlinear Hyperspectral Unmixing Methods

    Publication Year: 2014 , Page(s): 1844 - 1868
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1665 KB) |  | HTML iconHTML  

    In hyperspectral unmixing, the prevalent model used is the linear mixing model, and a large variety of techniques based on this model has been proposed to obtain endmembers and their abundances in hyperspectral imagery. However, it has been known for some time that nonlinear spectral mixing effects can be a crucial component in many real-world scenarios, such as planetary remote sensing, intimate mineral mixtures, vegetation canopies, or urban scenes. While several nonlinear mixing models have been proposed decades ago, only recently there has been a proliferation of nonlinear unmixing models and techniques in the signal processing literature. This paper aims to give an historical overview of the majority of nonlinear mixing models and nonlinear unmixing methods, and to explain some of the more popular techniques in detail. The main models and techniques treated are bilinear models, models for intimate mineral mixtures, radiosity-based approaches, ray tracing, neural networks, kernel methods, support vector machine techniques, manifold learning methods, piece-wise linear techniques, and detection methods for nonlinearity. Furthermore, we provide an overview of several recent developments in the nonlinear unmixing literature that do not belong into any of these categories. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 50. Efficient Framework for Palm Tree Detection in UAV Images

    Publication Year: 2014 , Article#: 2331425
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2292 KB) |  | HTML iconHTML  

    The latest developments in unmanned aerial vehicles (UAVs) and associated sensing systems make these platforms increasingly attractive to the remote sensing community. The large amount of spatial details contained in these images opens the door for advanced monitoring applications. In this paper, we use this cost-effective and attractive technology for the automatic detection of palm trees. Given a UAV image acquired over a palm farm, first we extract a set of keypoints using the Scale-invariant Feature Transform (SIFT). Then, we analyze these keypoints with an extreme learning machine (ELM) classifier a priori trained on a set of palm and no-palm keypoints. As output, the ELM classifier will mark each detected palm tree by several keypoints. Then, in order to capture the shape of each tree, we propose to merge these keypoints with an active contour method based on level sets (LSs). Finally, we further analyze the texture of the regions obtained by LS with local binary patterns (LBPs) to distinguish palm trees from other vegetations. Experimental results obtained on UAV images with 3.5 cm of spatial resolution and acquired over two different farms confirm the promising capabilities of the proposed framework. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (J-STARS) addresses current issues and techniques in applied remote and in situ sensing, their integration, and applied modeling and information creation for understanding the Earth.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Dr. Jocelyn Chanussot
Grenoble Institute of Technology