By Topic

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

Issue 1 • Date March 2011

Filter Results

Displaying Results 1 - 25 of 35
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (221 KB)  
    Freely Available from IEEE
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing publication information

    Page(s): C2
    Save to Project icon | Request Permissions | PDF file iconPDF (38 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (95 KB)  
    Freely Available from IEEE
  • Message from the Incoming Editor-in-Chief

    Page(s): 3 - 4
    Save to Project icon | Request Permissions | PDF file iconPDF (233 KB)  
    Freely Available from IEEE
  • Foreword to the Special Issue on “Human Settlements: A Global Remote Sensing Challenge”

    Page(s): 5 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (351 KB) |  | HTML iconHTML  

    This special issue follows the one in June 2008 and is related to the very successful series of the Joint Urban Remote Sensing Events, held every two years since 2005. Remote sensing of urban areas is at the moment facing a rapid development, due to the increasing amount of High Resolution (UR) and Very High Resolution VHR (VHR) data in both the optical/IR and microwave regions of the electromagnetic spectrum. On a global scale, human settlements have always been the focus of interest, but only in these days there starts to be an interest in mapping and monitoring even small and informal ones by satellites. Coherently, urban area mapping is moving from basic land cover to more complex land use maps, and human settlement environmental monitoring is committed to a more and more integrated use of remote sensing and in situ data. By presenting excellent papers on these subjects, this special issue tries and provides an overview of the state-of-the-art in this interesting field of applied earth observation and remote sensing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enumeration of Dwellings in Darfur Camps From GeoEye-1 Satellite Images Using Mathematical Morphology

    Page(s): 8 - 15
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1445 KB) |  | HTML iconHTML  

    This paper presents a methodology for the detection of dwelling structures in Darfur camps to estimate the total number of dwellings per camp using GeoEye-1 satellite images. The method is based on a translation of the visual characterization of the searched structures into a morphological image processing chain. Two variants are described: the first variant extracts dwellings fully automatic for enumeration, while the second links the area covered by dwellings to visual interpretation results of representative samples for estimation of the total number of dwellings. Compared to the visual interpretation both produce similar results with correlation coefficients of 0.65 and 0.66 respectively leading to a mean error of 6% in the total number of dwellings. In complex camp settings, the area-based approach might be preferred, since it provides some more control due to the visual interpretation included. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved Textural Built-Up Presence Index for Automatic Recognition of Human Settlements in Arid Regions With Scattered Vegetation

    Page(s): 16 - 26
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4042 KB) |  | HTML iconHTML  

    The so-called PANTEX methodology for the automatic recognition of built-up areas is based on analysis of image textural measures extracted using anisotropic rotation-invariant gray-level co-occurrence matrix (GLCM) statistics . These measures may overestimate the built-up areas in case of presence of scattered trees having the same spatial pattern of settlements. This overestimation is especially remarkable in case of bright soil background as in desert areas. In this paper we compare two options able to reduce this problem. One method is based on the subtraction of the vegetated areas from the built-up areas detected using the PANTEX index. The other method is based on the introduction of a morphological filtering step that pre-selects the image information to be ingested by the textural analysis phase. The test presented here uses multispectral Quick Bird satellite data input at the spatial resolution of 2.4 meters. In the selected test area, the application of the standard PANTEX procedure achieves the overall accuracy of 67.92%. The improvement of the procedure using the vegetation index achieves the accuracy of 70.37%, while the improvement based on morphological filtering achieves the accuracy of 88.69%, with an increase respect to the standard procedure of 2.44% and 20.76%, respectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Extraction of Urban Area Extents in HR and VHR SAR Images

    Page(s): 27 - 34
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (939 KB) |  | HTML iconHTML  

    This work is devoted to analyze the performance and adapt the parameters requested for the operational use of a methodology aimed at urban extent extraction. The procedure, initially proposed in a reduced version in a previous paper, has been expanded and improved to make it useful with different HR and VHR radar sensors, and extensive comparison of the results in many different parts of the world have been considered. In this work the approach is compared against reference settlement extents obtained from maps provided by the most relevant global mapping projects. Considerations about the robust ness of the approach to different spatial resolution, adaptiveness of the parameter range to the SAR sensor characteristics and other issues dealing with practical implementation of the whole procedures complete the research work discussed in these pages. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Comparison of High and Low Gain DMSP/OLS Satellite Images for the Study of Socio-Economic Metrics

    Page(s): 35 - 42
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (935 KB) |  | HTML iconHTML  

    The Operational Linescan System (OLS) onboard the Defense Meteorological Satellite Program (DMSP) group of satellites, unlike other passive remote sensing sensors, is capable of recording the emissions from artificial lights on the earth surface. Along with detecting light from forest fires, shipping fleets and gas flares, the OLS sensor also records the light emitted from cities at night. This paper reports on a study that uses the DMSP Operational Linescan (DMSP-OLS) images with fixed gain settings of 20 dB and 50 dB to model selected metrics used in the Indian census for the state of Maharashtra. The study firstly looks into the utility of non-composited single fixed gain radiance calibrated DMSP-OLS products for proposing a method which might help to build a surrogate method for Indian census. Several parameters are considered in this analysis, with detailed focus on population density, total population and proportion of households with electricity access for 35 districts within the state of Maharashtra. Results show that spatial scale plays an important role in selection of the images and gains. Secondly, this study provides a relative assessment of gain setting for the DMSP-OLS images in an urban Indian context. Images with a gain of 50 dB prove suitable for larger areas while those with a gain of 20 dB give better results at a smaller spatial scale. Statistical analysis and residual maps of spatial distribution of total population and population density validate the result. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Assessing Urban Environmental Quality Change of Indianapolis, United States, by the Remote Sensing and GIS Integration

    Page(s): 43 - 55
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1955 KB) |  | HTML iconHTML  

    Timely and regular information on urban environmental quality (UEQ) is essential for urban planning. This research evaluated the ten-year UEQ changes in Indianapolis, Indiana, U.S.A, based on the synthetic indicators of physical variables extracted from remotely sensed images and socioeconomic variables derived from census data. Physical environmental variables such as land use and land cover data, land surface temperature, normalized difference vegetation index, and other transformed remote sensing variables were derived from the two Landsat images taken in 1991 and 2000. Socioeconomic variables including population density, house characteristics, income, and education level were extracted from US census 1990 and 2000 block group (BG) data. Correlation analysis and factor analysis were performed after the two groups of variables were integrated at the BG level. For each year, four factors were identified and interpreted as greenness, crowdedness, economic status, and scenic amenity. By assigning different weights to each factor, two synthetic UEQ indexes were generated. A comparison of the two synthetic indexes revealed significant changes in UEQ pattern from 1990 to 2000. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monitoring Urban Sprawl Using Remote Sensing and GIS Techniques of a Fast Growing Urban Centre, India

    Page(s): 56 - 64
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2285 KB) |  | HTML iconHTML  

    India's urban population has grown tremendously in the last four decades from 79 million in 1961 to 285 million in 2001. This fast rate of increase in urban population is mainly due to large scale migration of people from rural and smaller towns to bigger cities in search of better employment opportunities and good life style. This rapid population pressure has resulted in unplanned growth in the urban areas to accommodate these migrant people which in turn leads to urban sprawl. It is a growing problematic aspect of metropolitan and bigger city's growth and development in recent years in India. Urban sprawl has resulted in loss of productive agricultural lands, open green spaces, loss of surface water bodies and depletion of ground water. Therefore, there is a need to study, understand and quantify the urban sprawl. In this paper an attempt has been made to use Shannon's entropy model to assess urban sprawl using IRS P-6 data and topographic sheet in GIS environment for one of the fastest growing city of South India and its surrounding area. The built-up area of the city has increased from 135 km2 in 1971 to 370 km2 in 2005. The study shows that there is a remarkable urban sprawl in and around the twin city between 1971 and 2005 because 215 km2 of agricultural land has lost to built-up land during this period. As a result the urban ecosystem has changed in the last four decades. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Urban Image Classification With Semisupervised Multiscale Cluster Kernels

    Page(s): 65 - 74
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1865 KB) |  | HTML iconHTML  

    This paper presents a semisupervised support vector machine (SVM) that integrates the information of both labeled and unlabeled pixels efficiently. Method's performance is illustrated in the relevant problem of very high resolution image classification of urban areas. The SVM is trained with the linear combination of two kernels: a base kernel working only with labeled examples is deformed by a likelihood kernel encoding similarities between labeled and unlabeled examples. Results obtained on very high resolution (VHR) multispectral and hyperspectral images show the relevance of the method in the context of urban image classification. Also, its simplicity and the few parameters involved make the method versatile and workable by unexperienced users. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated Vehicle Extraction and Speed Determination From QuickBird Satellite Images

    Page(s): 75 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1360 KB) |  | HTML iconHTML  

    A new method has been developed to automatically extract moving vehicles and subsequently determine their speeds from a pair of QuickBird (QB) panchromatic (PAN) and multispectral (MS) images. Since the PAN and MS sensors of QB have a slight time lag (approximately 0.2 s), the speed of a moving vehicle can be determined from the difference in the positions of the vehicle observed in the PAN and MS images due to the time lag. An object-based approach can be used to extract a vehicle from the PAN image, which has a resolution of 0.6 m. However, it is difficult to accurately extract the position of a vehicle from an MS image because its resolution is 2.4 m. Thus, an area correlation method is proposed to determine the location of a vehicle from an MS image at a sub-pixel level. The speed of the moving vehicle can then be calculated by using the vehicle extraction results. This approach was tested on several parts of a QB image covering central Tokyo, Japan, and the accuracy of the results is demonstrated in this study. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Building Detection From One Orthophoto and High-Resolution InSAR Data Using Conditional Random Fields

    Page(s): 83 - 91
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2436 KB) |  | HTML iconHTML  

    Today's airborne SAR sensors provide geometric resolution in the order well below half a meter. Many features of urban objects become visible in such data. However, layover and occlusion issues inevitably arise in urban areas complicating automated object detection. In order to support interpretation, SAR data may be analyzed using complementary information from maps or optical imagery. In this paper, an approach for building detection in urban areas based on object features extracted from high-resolution interferometric SAR (InSAR) data and one orthophoto is presented. Features describing local evidence as well as context information are used. Buildings are detected by classification of those feature vectors within a Conditional Random Field (CRF) framework. Although as graphical model similar to Markov Random Fields (MRF), CRFs have the advantage of incorporating global context information, of relaxing the conditional independence assumption between features, and of a more general integration of observations. We show that, first, CRFs perform well in comparison to Maximum Likelihood classifiers and MRFs. Second, the combined use of optical and InSAR features may improve detection results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time-Series InSAR Applications Over Urban Areas in China

    Page(s): 92 - 100
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2833 KB) |  | HTML iconHTML  

    In this study, we present the results achieved within the Dragon project, a cooperation program between the European Space Agency (ESA) and the National Remote Sensing Center of China (NRSCC), about monitoring subsidences and landslides in urban areas, analyzing cities growth and measuring the deformation of big man-made structures. Among the processed areas, we report here the main results we obtained in the test sites of Shanghai, Tianjin, Badong, and Three Gorges Dam. The techniques that have been used to process the data are original SAR interferometry (InSAR), Permanent Scatterers (PS-InSAR), Quasi-PS InSAR (QPS-InSAR), and a combination of coherent-uncoherent analysis. The results show that time-series InSAR techniques allow us to extract ground information with high spatial density and thus help us understanding the impact of urban development on terrain movements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Special Issue: Earth Observations and Remote Sensing for Environmental Management and Hazard Mitigation

    Page(s): 101 - 102
    Save to Project icon | Request Permissions | PDF file iconPDF (422 KB)  
    Freely Available from IEEE
  • A Multilevel Hierarchical Image Segmentation Method for Urban Impervious Surface Mapping Using Very High Resolution Imagery

    Page(s): 103 - 116
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2542 KB) |  | HTML iconHTML  

    This paper presents a hierarchical image segmentation method that combines multichannel watershed transformation and dynamics of watershed contours for the segmentation of very high resolution (VHR) multispectral imagery. The image gradient was first extracted from a multispectral image using a multichannel morphological method, followed by classical watershed transformation to produce an initial segmentation result. The resulting watershed contours were then analyzed according to their relevance relative to the minima of the adjacent basins to construct an image containing information about their dynamics. By thresholding the image of the contour dynamics at different levels, multilevel hierarchical segmentation results with different levels of detail were achieved. The proposed method was evaluated by comparing with existing methods through visual inspection, quantitative measures and applications in urban impervious surface mapping, using two sets of VHR image data. The experimental results showed that the proposed method produced more accurate segmentation results compared to an existing single-level segmentation method, in terms of visual and quantitative evaluations. While used for urban impervious surface mapping, the proposed method achieved an overall accuracy significantly higher than the pixel based classification method, and also higher than the object based classification using a single-level segmentation result. Compared with the most widely used segmentation method implemented in the eCognition, the proposed method achieved a comparable performance, although they have different segmentation details. The proposed segmentation method can be used in relevant VHR image processing and applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Soil Moisture Retrieval From AMSR-E Data in Xinjiang (China): Models and Validation

    Page(s): 117 - 127
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2202 KB) |  | HTML iconHTML  

    Accurate soil moisture information is required for studying the global water and energy cycles as well as the carbon cycle. The AMSR-E sensor onboard NASA's Aqua satellite offers a new means to accurately retrieve soil moisture information at a regional and global scale. However, the characterization of the factors such as precipitation, vegetation, cloud, ground roughness, and ice-snow packs is sensitive to the retrieval of the soil moisture content from the remotely sensed data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mapping Soil Moisture Using RADARSAT-2 Data and Local Autocorrelation Statistics

    Page(s): 128 - 137
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1746 KB) |  | HTML iconHTML  

    The purpose of this study is to evaluate the capability of surface radar backscatter models to estimate soil moisture over agricultural fields from fully polarimetric RADARSAT-2 C-band synthetic aperture radar (SAR) responses. For validation purposes, ground measurements over 44 sampling sites in eastern Ontario, Canada were carried out in the spring of 2008 simultaneously with satellite data acquisitions. Soil moisture retrieval was accomplished using two semi-empirical scattering models (Dubois and Oh) and the SAR image backscatter. Discrepancies between measured radar backscatter coefficients and those predicted by the models were previously reported, requiring correction factors to reduce biases associated with these semi-empirical approaches. Soil moisture was estimated by explicitly solving the two backscatter equations of the Dubois model, and using a look-up table (LUT) approach applied to the Oh model. Results showed that the Oh model in a cross-polarization (HH-HV) and Dubois in a co-polarization (HH-VV) inversion scheme provide the best estimates. These model configurations were implemented to produce multi-date soil moisture maps for the eastern Ontario site. To expand the range of validity of these soil moisture estimates, the maps produced by the Dubois and Oh models were uniquely combined. These estimates of absolute soil moisture were then used to derive spatial patterns of near-surface moisture content using the Getis statistic. The Getis statistic maps provide meaningful spatial information, demonstrating the potential of combining the Getis statistic and RADARSAT-2 data in predicting soil moisture conditions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum Nighttime Urban Heat Island (UHI) Intensity Simulation by Integrating Remotely Sensed Data and Meteorological Observations

    Page(s): 138 - 146
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1208 KB) |  | HTML iconHTML  

    Remote sensing of the urban heat island (UHI) effect has been conducted largely through simple correlation and regression between the UHI's spatial variations and surface characteristics. Few studies have examined the surface UHI from a temporal perspective and related it with climatic and meteorological factors. By selecting the city of Beijing, China, as the study area, the purpose of this research was to evaluate the applicability and feasibility of the support vector machine (SVM) technique to model the daily maximum nighttime UHI intensity (MNUHII) based on integration of MODIS land products and meteorological observations. First, a Gaussian surface model was used to calculate the city's MNUHIIs. Then, SVM regression models were developed to predict the MNUHII from the following variables: the normalized difference vegetation index (NDVI), surface albedo, atmospheric aerosol optical depth (AOD), relative humidity (RH), sunshine hour (SH), and precipitation (PREP). Results demonstrate that the accuracy of the SVM regression in predicting the MNUHII was around 0.8°C to 1.3°C; in addition, the SVM regression outperformed the multiple linear regression and the artificial neural network with backpropagation. A scenario analysis indicates that the relationships between the MNUHII and its influencing factors varied with time and season and were impacted by previous precipitation. The RH and AOD were the most important factors that influenced the MNUHII. In addition, previous precipitation could significantly mitigate the MNUHII. The results suggest that future investigations on the surface UHI effect should consider the climatic and meteorological conditions in addition to the surface characteristics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Synoptic Assessment of Repletion and Residual Water Dynamics in a Coastal Lagoon by Thermal Remote Sensing: Great Machipongo Lagoon (Hog Island Bay), Virginia, USA

    Page(s): 147 - 158
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3368 KB) |  | HTML iconHTML  

    Coastal lagoons are prominent features along many of the worlds sand coasts. Unlike estuaries, a large amount of lagoon volume is exchanged via tidal draining and repletion. We sought to quantify the repletion and residual water volumes in a coastal lagoon using satellite remote sensing. In the Great Machipongo Lagoon approximately 53% of the basin capacity drains out with each ebb tide, leaving a residual volume of about 47%. While the repletion footprint indicates the area of the lagoon that is completely flushed with each tide, residual water flushes at a much slower rate. The footprint of repletion water at full tide covers about 30% of the outer part of the lagoon. A fraction of the residual water is entrained into the repletion water mass along the plume frontal boundary. This allows a relatively small percent of the residual water to be exchanged with the coastal ocean. Thermal responses in ASTER imagery indicate zonation as well as areas of continuous mixing of repletion and residual waters. Comparison of remote sensing data with the tidal volume suggests that about 2-4% of the residual water mass is entrained along the frontal boundary during each tidal cycle and flushing of the residual water mass takes about 25-50 tidal cycles. The overall approach portends further application of thermal satellite remote sensing for monitoring estuarine and lagoon flushing and repletion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploration of Subsidence Estimation by Persistent Scatterer InSAR on Time Series of High Resolution TerraSAR-X Images

    Page(s): 159 - 170
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4263 KB) |  | HTML iconHTML  

    Ground subsidence is a major concern for land use planning and engineering risk assessment. This paper explores subsidence detection by the persistent scatterer (PS) interferometric synthetic aperture radar (InSAR) technique using the multitemporal high resolution spaceborne SAR images. We first describe the mathematical models and the data reduction procedures of the PS solution. The experiments of subsidence detection are then carried out over the Jinghai County in Tianjin (China) which has been sinking due to overuse of groundwater. The time series of high resolution SAR images collected by the X-band radar sensor onboard the satellite TerraSAR-X (TSX) are utilized for the PS detection, PS networking and subsidence estimation. The experimental results demonstrate that the high resolution of TSX SAR images can dramatically increase the PSs' density and coverage extent, especially in the built-up areas. Subsidence values can be extracted on the individual objects like buildings, street lamps and manhole covers, and on the linear engineering structures like the Jinghu high-speed railway. The PS InSAR with short radar wavelength (3.1 cm) is quite sensitive to ground displacement in the radar line-of-sight direction, and the derived subsidence measurements are in good agreement with the in situ data taken by optical leveling. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural Network Based Dunal Landform Mapping From Multispectral Images Using Texture Features

    Page(s): 171 - 184
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1766 KB) |  | HTML iconHTML  

    This paper presents a study towards machine generation of landform maps from optical remote sensing data. Our approach uses an offline trained multilayer perceptron (MLP) as a classifier, which is subsequently used to identify the landform classes in a satellite image. The paper emphasizes building a reasonably extensive database using multispectral images from which relevant texture information is computed. Gray level co-occurrence texture statistics, which form the feature vector representing the pattern, are used for training the MLP. Generalization results are assessed using the cross-validation mechanism. Performance of the algorithm is then extended to the problem of Aeolian (wind induced) landform mapping. Our results suggest that the textural method is promising for machine extraction of the landforms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recovering Reflectance of AQUA MODIS Band 6 Based on Within-Class Local Fitting

    Page(s): 185 - 192
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1254 KB) |  | HTML iconHTML  

    The Moderate Resolution Imaging Spectroradiometer (MODIS) aboard the Aqua satellite has been working well, except that 14 of the 20 detectors in Aqua MODIS band 6 (1.628-1.652 ) are ineffective. As a result, the periodic, along-scan strips in Aqua MODIS band 6 create problems in some high-level MODIS products. This paper demonstrates that MODIS bands 6 and 7 are highly correlated for each scene type. On this premise, we propose a within-class local fitting algorithm to recover missing reflectances of Aqua MODIS band 6. To test the efficacy of the proposed algorithm, experiments on real and simulated data are performed and the recovered images are evaluated qualitatively and quantitatively. The experimental results demonstrate that the proposed algorithm performs well. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bridging the Semantic Gap for Satellite Image Annotation and Automatic Mapping Applications

    Page(s): 193 - 204
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1565 KB) |  | HTML iconHTML  

    This paper brings a solution for bridging the gap between the results of state-of-the-art automatic classification algorithms and high semantic human-defined manually created terminology of cartographic data. Using a recent pure-spectral rule-based fully automatic classifier to define the basic 'vocabulary', we provide a hybrid method to automatically understand and describe semantic rules that link existent mapping data according to different specifications with the end-results of unsupervised computer information mining methods. Following an agreement between the learning model and the cartographic scale implied, we exploit Latent Dirichlet Allocation model (LDA) to map heterogeneous pixels with similar intermediate-level semantic meaning into land cover classes of various mapping products. By discovering the set of rules that explain semantic classes in existent vector systems, we introduce the prototype of an interactive learning loop that uses the concept of direct semantics applied on satellite imagery. We solve a big problem in generating cartographic information layers from a fully automatic classification map and demonstrate it for the typical case of Landsat images. 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