By Topic

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

Issue 6 • Date Dec. 2013

Filter Results

Displaying Results 1 - 25 of 28
  • [Front cover]

    Publication Year: 2013 , Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (406 KB)  
    Freely Available from IEEE
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing publication information

    Publication Year: 2013 , Page(s): C2
    Save to Project icon | Request Permissions | PDF file iconPDF (137 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2013 , Page(s): 2325 - 2326
    Save to Project icon | Request Permissions | PDF file iconPDF (156 KB)  
    Freely Available from IEEE
  • Airborne Vehicle Detection in Dense Urban Areas Using HoG Features and Disparity Maps

    Publication Year: 2013 , Page(s): 2327 - 2337
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2038 KB) |  | HTML iconHTML  

    Vehicle detection has been an important research field for years as there are a lot of valuable applications, ranging from support of traffic planners to real-time traffic management. Especially detection of cars in dense urban areas is of interest due to the high traffic volume and the limited space. In city areas many car-like objects (e.g., dormers) appear which might lead to confusion. Additionally, the inaccuracy of road databases supporting the extraction process has to be handled in a proper way. This paper describes an integrated real-time processing chain which utilizes multiple occurrence of objects in images. At least two subsequent images, data of exterior orientation, a global DEM, and a road database are used as input data. The segments of the road database are projected in the non-geocoded image using the corresponding height information from the global DEM. From amply masked road areas in both images a disparity map is calculated. This map is used to exclude elevated objects above a certain height (e.g., buildings and vegetation). Additionally, homogeneous areas are excluded by a fast region growing algorithm. Remaining parts of one input image are classified based on the `Histogram of oriented Gradients (HoG)' features. The implemented approach has been verified using image sections from two different flights and manually extracted ground truth data from the inner city of Munich. The evaluation shows a quality of up to 70 percent. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Vehicle Detection Method With High Resolution Highway Aerial Image

    Publication Year: 2013 , Page(s): 2338 - 2343
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2256 KB) |  | HTML iconHTML  

    A robust and efficient vehicle detection method from high resolution aerial image is still challenging. In this paper, a novel and robust method for automatic vehicle detection using aerial images over highway was presented. In the method, a GIS road vector map was used to constrain the vehicle detection system to the highway networks. After the morphological structure element was identified, we utilized the grayscale opening transformation and grayscale top-hat transformation to identify hypothesis vehicles in the light or white background, and used the grayscale closing transformation and grayscale bot-hat transformation to identify the hypothesis vehicles in the black or dark background. Then, targets with large size or covering a large area were sieved from the hypothesis vehicles using an area threshold that is much larger than a typical vehicle. Targets, whose width is narrower than the diameter of structure element utilized in the grayscale morphological transformation, were smoothed out from the hypothesis vehicles using binary morphological opening transformation. Finally, the hypothesis vehicles detected in both cases were overlaid. It should be noted that in the detection system, a vehicle could be detected twice by the two approaches. The two identical hypothesis vehicles should be amalgamated into a single one for accuracy assessment subsequently. We tested our system on seventeen highway scenes of aerial images with a spatial resolution of 0.15 × 0.15 m. The experimental results showed that the correctness, completeness, and quality rates of the proposed vehicle detection method were about 98%, 93%, and 92%, respectively. Thus, our proposed approach is robust and efficient to detect vehicles of highway using high resolution aerial images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of Localized Surface Uplift by Differential SAR Interferometry at the Hangingstone Oil Sand Field, Alberta, Canada

    Publication Year: 2013 , Page(s): 2344 - 2354
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3617 KB) |  | HTML iconHTML  

    We estimated the surface uplift (heave) rate due to steam-assisted gravity drainage (SAGD) at the Hangingstone oil sand field in Alberta, Canada, by stacking differential synthetic aperture radar (SAR) interferograms. To improve accuracy, a Landsat-7 Enhanced Thematic Mapper Plus intensity image was coregistered with the SAR intensity image. We examined three interferogram filtering methods and identified one that provided the desired effect of light filtering in areas of low noise and heavier filtering in high-noise areas. Based on our analysis of interferogram coherences, site-specific decorrelation highly depends on local seasonal changes. Stacking was performed to estimate the surface uplift rate while removing atmospheric and seasonal effects. The amounts of the uplift rate and slope change estimated by means of InSAR analysis reached a maximum of 3.6 cm/yr and 0.003%, respectively, for the period of 2007-2008. Comparison of the magnitude and patterns of the estimated surface uplift demonstrated that the uplift estimated from InSAR analysis agrees well with that obtained by conventional geodetic (GPS) surveys from a network of 54 monuments. Surface slope changes due to SAGD that we detected by using InSAR over one year in this oil sand field were small, so destruction of surface facilities by uplift is unlikely in the short term. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Satellite Oil Spill Detection Using Artificial Neural Networks

    Publication Year: 2013 , Page(s): 2355 - 2363
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3269 KB) |  | HTML iconHTML  

    Oil spills represent a major threat to ocean ecosystems and their health. Illicit pollution requires continuous monitoring and satellite remote sensing technology represents an attractive option for operational oil spill detection. Previous studies have shown that active microwave satellite sensors, particularly Synthetic Aperture Radar (SAR) can be effectively used for the detection and classification of oil spills. Oil spills appear as dark spots in SAR images. However, similar dark spots may arise from a range of unrelated meteorological and oceanographic phenomena, resulting in misidentification. A major focus of research in this area is the development of algorithms to distinguish oil spills from `look-alikes'. This paper describes the development of a new approach to SAR oil spill detection employing two different Artificial Neural Networks (ANN), used in sequence. The first ANN segments a SAR image to identify pixels belonging to candidate oil spill features. A set of statistical feature parameters are then extracted and used to drive a second ANN which classifies objects into oil spills or look-alikes. The proposed algorithm was trained using 97 ERS-2 SAR and ENVSAT ASAR images of individual verified oil spills or/and look-alikes. The algorithm was validated using a large dataset comprising full-swath images and correctly identified 91.6% of reported oil spills and 98.3% of look-alike phenomena. The segmentation stage of the new technique outperformed the established edge detection and adaptive thresholding approaches. An analysis of feature descriptors highlighted the importance of image gradient information in the classification stage. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quality Analysis of NRTK Positioning on Boundary Regions and Under Unfavorable Topographic Conditions in the Southern Iberian Peninsula

    Publication Year: 2013 , Page(s): 2364 - 2374
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2658 KB) |  | HTML iconHTML  

    The aim of this paper is to check the precision, accuracy and repeatability of network-based real time kinematic (NRTK) positioning under favorable (rover located inside the active network, close to the reference stations and at a similar altitude) and nonfavorable conditions (near to the boundaries region and at greater distances and elevation differences from the nearest reference stations). The rover location with respect to the reference stations is a crucial factor, especially in boundaries regions where favorable geometry cannot be assured. The elevation difference between the rover position and the nearest reference stations is also decisive. If the residual tropospheric delay is not modeled carefully there will be a bias error in the vertical component. This affects the precision of NRTK positioning, especially in the altimetric component. In order to analyze the NRTK positioning based on the Andalusian positioning network (RAP), three “nonsimulated” network scenarios (real outside and inside test sites/data are used) with different topography and environmental conditions in Southern Spain are presented: central area of Andalusia with full network coverage and the northern and southern borders of the region which are characterized as a mountainous and a coastal area, respectively. In the last two the network corrections are extrapolated. The statistical results confirm that it is possible to achieve centimeter-scale accuracy with NRTK positioning based on the RAP network even in border and coastal areas of Andalusia. However, the numerical results for each test site may be taken into consideration in proposing local improvements in the RAP network. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Assimilation of Passive Microwave Streamflow Signals for Improving Flood Forecasting: A First Study in Cubango River Basin, Africa

    Publication Year: 2013 , Page(s): 2375 - 2390
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2541 KB) |  | HTML iconHTML  

    Floods are among the most frequently occurring and disastrous natural hazards in the world. The overarching goal of this study is to investigate the utility of passive microwave AMSR-E signal and TRMM based precipitation estimates in improving flood prediction at the sparsely gauged Cubango River Basin, Africa. This is accomplished by coupling a widely used conceptual rainfall-runoff hydrological model with Ensemble Square Root Filter (EnSRF) to account for uncertainty in both forcing data and model initial conditions. Three experiments were designed to quantify the contributions of the AMSR-E signal to the flood prediction accuracy, in comparison to the benchmark assimilation of in-situ streamflow observations, for both “Open Loop” and “Assimilation” modules. In general, the EnSRF assimilation of both in-situ observations and AMSR-E signal-converted-streamflow effectively improved streamflow modeling performance in terms of three statistical measures. In order to further investigate AMSR-E signals' contribution to extreme events prediction skill, the upper 10th percentile daily streamflow was taken as the threshold. Results show significantly improved skill and detectability of floods as well as reduced false alarm rates. Given the global availability of satellite-based precipitation from current TRMM and future GPM, together with soil moisture information from the current AMSR-E and future SMAP mission at near real-time, this “first attempt” study at a sparsely gauged African basin shows that opportunities exist for an integrated application of a suite of satellite data in improving flood forecasting worldwide by careful fusion of remote sensing and in-situ observations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wetlands Mapping in North America by Decision Rule Classification Using MODIS and Ancillary Data

    Publication Year: 2013 , Page(s): 2391 - 2401
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1282 KB) |  | HTML iconHTML  

    An up-to-date wetlands map based on remote sensing data at a continental scale is urgently needed for estimating global environmental change. In this study, a wetlands map of North America was developed using Moderate Resolution Imaging Spectroradiometer (MODIS) data obtained in 2008 and ancillary data. For this purpose, a decision rule classification method was developed relied upon the hierarchical characteristics of land types and prior knowledge about the geographical location of wetlands. Two hierarchical levels of land types were used to extract wetlands. At the first level, non-vegetation land types including water, snow, urban, and bare areas were separately extracted from vegetation land types using threshold methods. At the second level, wetlands were discriminated from non-wetland vegetation land types with the MODIS tasseled cap (brightness, greenness, and wetness) indices using the decision tree method. In addition, elevation data were used to build the elevation mask and a climate map was used to subdivide the study area into five sub-regions. In the quantitative accuracy assessment, user's and producer's accuracies of wetlands for the whole study area were calculated as 80.3% and 83.7%, respectively. In a comparison with two existing global land cover datasets, GLC2000 and IGBP DISCover, our results show significant improvement in extracting coastal and narrow types of wetlands. This study indicates that decision rule classification, integrated with multi-temporal MODIS data and ancillary data, is useful to develop an improved wetlands map at a continental scale. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Globally Statistical Active Contour Model for Segmentation of Oil Slick in SAR Imagery

    Publication Year: 2013 , Page(s): 2402 - 2409
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3087 KB) |  | HTML iconHTML  

    Robust and accurate segmentation of the oil slick from SAR imagery is a key step for the detection and monitoring of oil spills, whose observation is very important for protecting the marine environments. However, intensity inhomogeneity, noise, and weak boundary often exist in the oil slick region in SAR imagery, making the accurate segmentation of oil slick very challenging. In this paper, we propose a novel statistical active contour model for oil slick segmentation. First, we fit the distributions of the inhomogeneous intensity with Gaussian distributions of different means and variances. Then, a moving window is used to map the original image intensity into another domain, where the intensity distributions of inhomogeneous objects are still Gaussian but are better separated. In the transformed domain, the means of the Gaussian distributions can be adaptively estimated by multiplying a smooth function with the signal within the window. Thereafter, for each local region, we define a statistical energy function, which combines the smooth function, the level set function, and the constant approximating the true signal from the corresponding object. In addition, in order to make the final segmentation robust to the initialization of level set function, we present a new energy function which is convex with respect to the level set function, thereby avoiding the local minima. An efficient iterative algorithm is then proposed to minimize the energy function that makes the segmentation robust. Experiments undertaken using some challenging SAR oil slick images demonstrate the superiority of our proposed algorithm with respect to the state-of-the-art representative methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Urbanization Detection by a Region Based Mixed Information Change Analysis Between Built-Up Indicators

    Publication Year: 2013 , Page(s): 2410 - 2420
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2589 KB) |  | HTML iconHTML  

    A method for analyzing the urbanization process from multitemporal SPOT 5 panchromatic images is presented. The analysis is performed by unsupervised change detection between built-up presence indicators extracted separately from the scenes. The obtained index has an effective resolution which is coarser than the Ground Sample Distance, thus allowing a good spatial match between the indicators. Then, a local Mixed Information change indicator is employed in order to capture the non-linear temporal behaviors. A region-based approach is developed in synergy with the local Mixed Information in order to process consistently large scenes which may be affected by regional acquisition distortions. Experiments are conducted on SPOT 5 scenes acquired in 2003 and 2008 which cover a suburban area (45×45 km2) of the city of Tangshan in China. The urbanization detector is validated by visual interpretation, giving an equal omission/commission probability of 10%. A comparison to linear change indicators highlights an improvement of 15% of the equal omission/commission probability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense Regional Active Networks and High Accuracy Positioning Services. A Case Study Based on the Andalusian Positioning Network (Southern Spain)

    Publication Year: 2013 , Page(s): 2421 - 2433
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5616 KB) |  | HTML iconHTML  

    Today, a great number of regional-scale active networks are established all over the world for multiple applications. High accuracy real time positioning services are provided via Internet and continuous GNSS data from permanent stations are freely available through public data files for post-processing. Both solutions should be referred to a compatible realization of European Terrestrial Reference System when they are combined. This paper presents the current status of a regional active network in southern Spain (Andalusian Positioning Network, RAP) and analyzes the difference, in terms of availability, time required to fix ambiguities, precision, accuracy and repeatability of RTK positioning, between single-base Real Time Kinematic (RTK) and network RTK (NRTK) approaches, both based on this dense active network. To check the RTK performance an extensive process control was undertaken across Andalusia (Southern Spain). The initial results of the tests applied on 60 geodetic sites are presented. The tests results show that, in the case of regional active networks with distances “reference-rover” less than 30 km, NRTK and nearest single-base RTK solutions present the same level of precision and accuracy. The spatial distribution of RAP stations guarantees an effective coverage within the region, but their altimetric distribution should be adjusted to the actual terrain morphology in order to achieve reliable, homogeneous and high accuracy positioning across the network. The results achieved in this applied research may be of interest to RAP users and also to other regional and local networks covering a similar area and with analogous structural characteristics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Integrated Optical Remote Sensing System for Environmental Perturbation Research

    Publication Year: 2013 , Page(s): 2434 - 2444
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2045 KB) |  | HTML iconHTML  

    Remote sensing is the only technology that can systematically monitor physical properties of the biosphere over a vast region. However, it is still a challenge to make these measures meaningful for assessing the impacts of environmental perturbation. Here, we integrate an optical remote sensing system termed EcoiRS (Ecosystem observation by an integrated Remote Sensing system) specifically for this purpose. EcoiRS consists of three subsystems: an off-the-shelf atmospheric correction model (ACORN), a cloud/shadow removal model, and an advanced spectral mixture analysis model (AutoMCU). The core of ACORN is a set of radiative transfer codes that can be used to remove the effects of molecular/aerosol scatterings and water vapor absorption from remotely sensed data, and to convert these digital signals to surface reflectance. Shadow and cloud cover that would obscure the reflective properties of land surfaces in an image can be minimized by referring to their optical and thermal spectral profiles. AutoMCU executes iterative unmixing for each pixel using selected spectral endmembers based upon the rule of Monte Carlo simulation. The main outcomes of EcoiRS include cover fractions of green vegetation, non-photosynthetically active vegetation and bare soils, along with uncertainty measures for each pixel. The dynamics of these derived products are significant indicators for monitoring the change of states of terrestrial environments, and they can be used for investigating different environmental perturbations. Here, we demonstrate studies of implementing EcoiRS to map three major but relatively less studied cases in a western Pacific island (Taiwan): typhoons, tree diseases and alien plant invasion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 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.
  • Mapping Open Space in an Old-Growth, Secondary-Growth, and Selectively-Logged Tropical Rainforest Using Discrete Return LIDAR

    Publication Year: 2013 , Page(s): 2453 - 2461
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1449 KB) |  | HTML iconHTML  

    Light detection and ranging (LIDAR) is a valuable tool for mapping vegetation structure in dense forests. Although several LIDAR-derived metrics have been proposed for characterizing vertical forest structure in previous studies, none of these metrics explicitly measure open space, or vertical gaps, under a forest canopy. We develop new LIDAR metrics that characterize vertical gaps within a forest for use in forestry and forest management applications. The proposed metrics are extracted from discrete return LIDAR data acquired over the La Selva Biological Station, Costa Rica across three different forest management types (old-growth, secondary-growth, and selectively-logged). A comparison to common LIDAR metrics of vertical vegetation structure revealed that our new metrics provide unique information about the structure of the forest canopy. Maps showing the distribution of vertical gap and complex canopy patches identified from our LIDAR metrics demonstrate that the pattern of open space in tropical rain forests is linked to forest management strategies. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatial-Spectral Kernel Sparse Representation for Hyperspectral Image Classification

    Publication Year: 2013 , Page(s): 2462 - 2471
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2874 KB) |  | HTML iconHTML  

    Kernel sparse representation classification (KSRC), a nonlinear extension of sparse representation classification, shows its good performance for hyperspectral image classification. However, KSRC only considers the spectra of unordered pixels, without incorporating information on the spatially adjacent data. This paper proposes a neighboring filtering kernel to spatial-spectral kernel sparse representation for enhanced classification of hyperspectral images. The novelty of this work consists in: 1) presenting a framework of spatial-spectral KSRC; and 2) measuring the spatial similarity by means of neighborhood filtering in the kernel feature space. Experiments on several hyperspectral images demonstrate the effectiveness of the presented method, and the proposed neighboring filtering kernel outperforms the existing spatial-spectral kernels. In addition, the proposed spatial-spectral KSRC opens a wide field for future developments in which filtering methods can be easily incorporated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Saliency for Spectral Image Analysis

    Publication Year: 2013 , Page(s): 2472 - 2479
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1486 KB) |  | HTML iconHTML  

    We introduce a new feature extraction model for purposes of image comparison, visualization and interpretation. We define the notion of spectral saliency, as the extent to which a certain group of pixels stands out in an image and in terms of reflectance, rather than in terms of colorimetric attributes as it is the case in traditional saliency studies. The model takes as an input a multi- or hyper-spectral image with any dimensionality, any range of wavelengths, and it uses a series of dedicated feature extractions to output a single saliency map. We also present a local analysis of the image spectrum allowing to produce such maps in color, thus depicting not only which objects are salients, but also in which range of wavelengths. A variety of applications can be derived from the resulting maps, particularly under the scope of visualization, such as the saliency-driven evaluation of dimensionality reduction techniques. Results show that spectral saliency provides valuable information, which do not correlate neither with visual saliency, second-order statistics nor with naturalness, but serve however well for visualization-related applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of Dust Storms Using MODIS Reflective and Emissive Bands

    Publication Year: 2013 , Page(s): 2480 - 2485
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (943 KB) |  | HTML iconHTML  

    Dust storms are one of the natural phenomena, which have increased in frequency in recent years in North Africa, Australia and northern China. Satellite remote sensing is the common method for monitoring dust storms but its use for identifying dust storms over sandy ground is still limited as the two share similar characteristics. In this study, an artificial neural network (ANN) is used to detect dust storm using 46 sets of data acquired between 2001 and 2010 over North Africa by the Moderate Resolution Imaging Spectroradiometer (MODIS) instruments aboard the Terra and Aqua satellites. The ANN uses image data generated from Brightness Temperature Difference (BTD) between bands 23 and 31 and BTD between bands 31 and 32 with three bands 1, 3, and 4, to classify individual pixels on the basis of their multiple-band values. In comparison with the manually detection of dust storms, the ANN approach gave better result than the Thermal Infrared Integrated Dust Index approach for dust storms detection over the Sahara. The trained ANN using data from the Sahara desert gave an accuracy of 0.88 when tested on data from the Gobi desert and managed to detect 90 out of the 96 dust storm events captured worldwide by Terra and Aqua satellites in 2011 that were classified as dusty images on NASA Earth Observatory. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Porting Existing Radiation Code for GPU Acceleration

    Publication Year: 2013 , Page(s): 2486 - 2491
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (664 KB) |  | HTML iconHTML  

    Graphics processing units (GPUs) have proven very robust architectures for performing intensive scientific calculations, resulting in speedups as high as several hundred times. In this paper, the GPU acceleration of a radiation code for use in creating simulated satellite observations of predicted climate change scenarios is explored, particularly the prospect of porting an already existing and widely used radiation transport code to a GPU version that fully exploits the parallel nature of GPUs. The porting process is attempted with a simple radiation code, revealing that this process centers on creating many copies of variables and inlining function/subroutine calls. A resulting speedup of about 25x is reached. This is less than the speedup achieved from a radiation code built for CUDA from scratch, but it was achieved with an already existing radiation code using the PGI Accelerator to automatically generate CUDA kernels, and this demonstrates a possible strategy to speed up other existing models like MODTRAN and LBLRTM. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization of Object-Based Image Analysis With Random Forests for Land Cover Mapping

    Publication Year: 2013 , Page(s): 2492 - 2504
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3087 KB) |  | HTML iconHTML  

    A prerequisite for object-based image analysis is the generation of adequate segments. However, the parameters for the image segmentation algorithms are often manually defined. Therefore, the generation of an ideal segmentation level is usually costly and user-depended. In this paper a strategy for a semi-automatic optimization of object-based classification of multitemporal data is introduced by using Random Forest (RF) and a novel segmentation algorithm. The Superpixel Contour (SPc) algorithm is used to generate a set of different levels of segmentation, using various combinations of parameters in a user-defined range. Finally, the best parameter combination is selected based on the cross-validation-like out-of-bag (OOB) error that is provided by RF. Therefore, the quality of the parameters and the corresponding segmentation level can be assessed in terms of the classification accuracy, without providing additional independent test data. To evaluate the potential of the proposed concept, we focus on land cover classification of two study areas, using multitemporal RapidEye and SPOT 5 images. A classification that is based on eCognition's widely used multiresolution segmentation algorithm (MRS) is used for comparison. Experimental results underline that the two segmentation algorithms SPc and MRS perform similar in terms of accuracy and visual interpretation. The proposed strategy that uses the OOB error for the selection of the ideal segmentation level provides similar classification accuracies, when compared to the results achieved by manual-based image segmentation. Overall, the proposed strategy is operational and easy to handle and thus economizes the findings of optimal segmentation parameters for the Superpixel Contour algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Remote Sensing of Water Optical Property for China's Inland Lake Taihu Using the SWIR Atmospheric Correction With 1640 and 2130 nm Bands

    Publication Year: 2013 , Page(s): 2505 - 2516
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3327 KB) |  | HTML iconHTML  

    Using the shortwave infrared (SWIR) atmospheric correction algorithm with 1640 and 2130 nm bands, water optical property data for China's inland freshwater Lake Taihu have been derived from measurements of the Moderate Resolution Imaging Spectroradiometer (MODIS) on the satellite Aqua. Using MODIS-Aqua measurements from 2002 to 2010, seasonal and spatial distributions of the normalized water-leaving radiance nLw(λ) spectra from visible to the near-infrared (NIR) and SWIR (1240 nm) are derived and used for study and characterization of Lake Taihu water optical properties. In particular, for the first time, spatial and seasonal variations of nLw(λ) at the SWIR 1240 nm (nLw(1240)) are derived for the lake and show some different features from those of the red and NIR nLw(λ) (nLw (645) and nLw (859)). Time series of monthly MODIS-derived nLw(λ) spectra for Lake Taihu are obtained and analyzed, showing important seasonal and interannual variations. The results indicate that the SWIR nLw (1240) contributions in the lake are mainly due to the presence of significant amounts of algae, while the red and NIR nLw(λ) variations result from changes of total suspended sediment (TSS) amounts in the water column. Furthermore, this study shows that all three SWIR bands at 1240, 1640, and 2130 nm are useful and required for satellite water quality remote sensing for extremely turbid near-shore and inland waters. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oil Spill Mapping and Measurement in the Gulf of Mexico With Textural Classifier Neural Network Algorithm (TCNNA)

    Publication Year: 2013 , Page(s): 2517 - 2525
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3430 KB) |  | HTML iconHTML  

    We developed a Textural Classifier Neural Network Algorithm (TCNNA) to process Synthetic Aperture Radar (SAR) data to map oil spills. The algorithm processes SAR data and wind model outputs (CMOD5) using a combination of two neural networks. The first neural network filters out areas of the image that do not need to be processed by flagging pixels as oil candidates; the second neural network performs a statistical textural analysis to differentiate between pixels of sea surface with or without floating oil. By combining the two neural networks, we are able to process a full resolution geotiff SAR image (16 bit, ~ 350 MB) in less than one minute on a conventional PC. The algorithm performs efficiently for all radar incidence angles when wind conditions are above 3 m/s. When low wind conditions are present, the performance of the neural network classification is limited, however the algorithm output allows the user to easily discard any elements of the classification and export the final product as a map of the water covered by oil. The results of this algorithm allowed us to process rapidly all of the images collected by Envisat during the Gulf of Mexico (GOM) Deepwater Horizon (DWH) oil spill event. By normalizing oil detections by the frequency that each area was sampled, we estimate that oil covered a mean daily area of 10,750 km2 (with a total extent of 119,600 km2 of the GOM surface waters), and approximately 1,300 km of the Northern GOM shoreline was threatened by the presence of drifting oil. View full abstract»

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

    Publication Year: 2013 , Page(s): 2526
    Save to Project icon | Request Permissions | PDF file iconPDF (771 KB)  
    Freely Available from IEEE
  • IEEE Copyright Form

    Publication Year: 2013 , Page(s): 2527 - 2528
    Save to Project icon | Request Permissions | PDF file iconPDF (1590 KB)  
    Freely Available from IEEE

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