Search

Urban land use classification is significant for urban development planning. Considering complex environments of urban surface features, traditional semantic segmentation methods are difficult to solve the problems of mixed pixels and limited spatial resolution of images. The subpixel mapping technology is an effective method to solve the above problems in urban land use classification. However, traditional subpixel mapping methods are sensitive to mountain shadow, high-rise building shadow and impermeable surface heterogeneity, resulting in false classification. Therefore, we propose a subpixel mapping method that can reduce the shadow effect. This method uses a multi-index feature fusion strategy to optimize the abundance of the shadow errors in the abundance image, and uses a super-resolution reconstruction neural network model to reconstruct the optimized abundance image for the subpixel mapping of urban land use. Experiments were conducted on sentinel-2 images obtained over Yuelu District of Changsha City, Hunan Province, China. The experimental results show that the method proposed in this article can effectively overcome the influence of building shadows and mountain shadows in urban land cover classification and is superior to traditional subpixel/pixel spatial attraction model, radial basis function, super-resolution subpixel mapping, and other methods in the effect and accuracy of urban land use subpixel mapping.

The unavoidable nature of Ulva prolifera mixed pixel in low-resolution remote sensing images would result in rough boundary of U. prolifera patches, omission of tiny patches, and overestimation of coverage area. The decomposition of U. prolifera mixed pixel addresses the issue of coverage area overestimation, and the remaining problems can be alleviated by subpixel mapping (SPM). Due to the drift and dissipation of U. prolifera, a suitable SPM method is the single image-based unsupervised method. However, the method has difficulties in detail reconstruction, insufficient learning of spectral information, and SPM error introduced by abundance deviation. Therefore, we proposed a multiple-feature decision fusion SPM (MFDFSPM) method. It involves three branches to obtain the spatial, abundance, and spectral features of U. prolifera while considers multi-feature information using the fusion strategy. Experiments on the Geostationary Ocean Color Imager images in the Yellow Sea of China indicate that the MFDFSPM overperforms several typical U. prolifera SPM methods in higher accuracy and stronger robustness in both SPM and abundance calculation, which produced subpixel map with more detailed spatial information and less noise. [ABSTRACT FROM AUTHOR]

To achieve land cover change detection (LCCD) with both fine spatial and temporal resolutions from remote sensing images, subpixel mapping-based approaches have been widely studied in recent years. The fine spatial but coarse temporal resolution image and the coarse spatial but fine temporal image are used to accomplish LCCD by combining their advantages. However, the performance of subpixel mapping is easily affected by the accuracy of spectral unmixing, thereby reducing the reliability of LCCD. In this article, a novel subpixel change detection scheme based on improved abundance values is proposed to tackle the aforementioned problem, in which the spatial distribution of fine spatial resolution image is borrowed to promote the accuracy of spectral unmixing. First, the coarse spatial resolution image is used to generate the original abundance image by the spectral unmixing method. Second, the spatial distribution information of the fine spatial resolution image is incorporated into the original abundance image to obtain improved abundance values. Third, the fine spatial resolution subpixel map can be generated by the subpixel mapping method using the improved abundance values. At last, the fine resolution change map can be obtained by comparing the subpixel map with the fine spatial resolution image. Experiments are conducted on a simulated dataset based on Landsat-7 images and two real datasets based on Landsat-8 and MODIS images. The results of the real datasets showed that the proposed method can effectively improve the performance of LCCD with an overall accuracy of approximately 1.26% and 0.79% to the existing methods.

The accurate detection of burned forest area is essential for post-fire management and assessment, and for quantifying carbon budgets. Therefore, it is imperative to map burned areas accurately. Currently, there are few burned-area products around the world. Researchers have mapped burned areas directly at the pixel level that is usually a mixture of burned area and other land cover types. In order to improve the burned area mapping at subpixel level, we proposed a Burned Area Subpixel Mapping (BASM) workflow to map burned areas at the subpixel level. We then applied the workflow to Sentinel 2 data sets to obtain burned area mapping at subpixel level. In this study, the information of true fire scar was provided by the Department of Emergency Management of Hunan Province, China. To validate the accuracy of the BASM workflow for detecting burned areas at the subpixel level, we applied the workflow to the Sentinel 2 image data and then compared the detected burned area at subpixel level with in situ measurements at fifteen fire-scar reference sites located in Hunan Province, China. Results show the proposed method generated successfully burned area at the subpixel level. The methods, especially the BASM-Feature Extraction Rule Based (BASM-FERB) method, could minimize misclassification and effects due to noise more effectively compared with the BASM-Random Forest (BASM-RF), BASM-Backpropagation Neural Net (BASM-BPNN), BASM-Support Vector Machine (BASM-SVM), and BASM-notra methods. We conducted a comparison study among BASM-FERB, BASM-RF, BASM-BPNN, BASM-SVM, and BASM-notra using five accuracy evaluation indices, i.e., overall accuracy (OA), user's accuracy (UA), producer's accuracy (PA), intersection over union (IoU), and Kappa coefficient (Kappa). The detection accuracy of burned area at the subpixel level by BASM-FERB's OA, UA, IoU, and Kappa is 98.11%, 81.72%, 74.32%, and 83.98%, respectively, better than BASM-RF's, BASM-BPNN's, BASM-SVM's, and BASM-notra's, even though BASM-RF's and BASM-notra's average PA is higher than BASM-FERB's, with 89.97%, 91.36%, and 89.52%, respectively. We conclude that the newly proposed BASM workflow can map burned areas at the subpixel level, providing greater accuracy in regards to the burned area for post-forest fire management and assessment. [ABSTRACT FROM AUTHOR]

The fine extraction of water boundaries is of great significance for water resource monitoring, water environment monitoring, and flood prevention. MODIS images are widely used for water extraction due to their high temporal resolution, wide coverage, gratuity, and long observation period. However, owing to their low spatial resolution, the water boundary results are often blurred. It is difficult to extract water boundaries accurately. The subpixel mapping algorithm can solve this problem. In this article, Dongting Lake and its surroundings are adopted as the experimental area. The digital elevation model (DEM) is used to modify the subpixel/pixel spatial attraction model (SPSAM) mapping results. The proposed algorithm is referred to as the DEM-modified SPSAM (D-MSPSAM). Based on the visual results of the two sets of experiments, the modified results suitably maintain the spatial details of the water, and many of the underestimations caused by the similarity of the spectral characteristics of the surroundings to those of the water have been corrected. In this paper, the accuracy of Landsat-8 water extraction is used as a reference. Based on the quantitative results, the D-MSPSAM method has a higher extraction accuracy than the traditional threshold method, and the accuracies of the extraction for high water and low water have been increased by 3.56 percentage points and 2.77 percentage points, respectively. Furthermore, these results also confirm the potential application of DEM data for flood submergence extraction and provide new ideas for the improvement of the subpixel mapping model. The proposed method can accurately generate water distribution maps in a practical and economical way.

Classification at subpixel level for a low resolution hyperspectral image (LR HSI) is considered in this article. Using selected labeled samples as labeled endmembers and unsupervised clustering centers of LR HSI as unlabeled endmembers, a hybrid endmember library is constructed for spectral unmixing of LR HSI. The abundances of unlabeled endmembers are used to optimize the estimated fractional abundances of labeled classes within mixed pixels to improve the estimation accuracy. A more accurate subpixel mapping result is then obtained by applying subpixel spatial attraction model with the optimized fractional abundances. To incorporate spatial contextual information and further improve the subpixel mapping performance, a subpixel level segmentation map is generated by applying unsupervised clustering to the upsampled LR HSI, and integrated with the initial subpixel mapping result by decision fusion. Experimental results demonstrate that the proposed method remarkably outperforms state-of-the-art subpixel mapping methods, including the corresponding ones with or without spatial contextual information incorporation.

The accurate detection of burned forest area is essential for post-fire management and assessment, and for quantifying carbon budgets. Therefore, it is imperative to map burned areas accurately. Currently, there are few burned-area products around the world. Researchers have mapped burned areas directly at the pixel level that is usually a mixture of burned area and other land cover types. In order to improve the burned area mapping at subpixel level, we proposed a Burned Area Subpixel Mapping (BASM) workflow to map burned areas at the subpixel level. We then applied the workflow to Sentinel 2 data sets to obtain burned area mapping at subpixel level. In this study, the information of true fire scar was provided by the Department of Emergency Management of Hunan Province, China. To validate the accuracy of the BASM workflow for detecting burned areas at the subpixel level, we applied the workflow to the Sentinel 2 image data and then compared the detected burned area at subpixel level with in situ measurements at fifteen fire-scar reference sites located in Hunan Province, China. Results show the proposed method generated successfully burned area at the subpixel level. The methods, especially the BASM-Feature Extraction Rule Based (BASM-FERB) method, could minimize misclassification and effects due to noise more effectively compared with the BASM-Random Forest (BASM-RF), BASM-Backpropagation Neural Net (BASM-BPNN), BASM-Support Vector Machine (BASM-SVM), and BASM-notra methods. We conducted a comparison study among BASM-FERB, BASM-RF, BASM-BPNN, BASM-SVM, and BASM-notra using five accuracy evaluation indices, i.e., overall accuracy (OA), user’s accuracy (UA), producer’s accuracy (PA), intersection over union (IoU), and Kappa coefficient (Kappa). The detection accuracy of burned area at the subpixel level by BASM-FERB’s OA, UA, IoU, and Kappa is 98.11%, 81.72%, 74.32%, and 83.98%, respectively, better than BASM-RF’s, BASM-BPNN’s, BASM-SVM’s, and BASM-notra’s, even though BASM-RF’s and BASM-notra’s average PA is higher than BASM-FERB’s, with 89.97%, 91.36%, and 89.52%, respectively. We conclude that the newly proposed BASM workflow can map burned areas at the subpixel level, providing greater accuracy in regards to the burned area for post-forest fire management and assessment.

Monitoring unlawful constructions in cultural relic sites is difficult in remote and unpopulated areas. This paper aims at facilitating cultural relic protection surveys using remote sensing. High-resolution remote sensing images are better alternatives to field visits for locating unlawful buildings. However, these buildings are usually hidden by vast wildness around the cultural relics, which makes the use of high-resolution imagery costly and inefficient. The main purpose of this research is to develop an approach to subpixel building identification from moderate resolution images, such as Landsat 8 OLI with reasonable accuracy based on the mixture-tuned match filtering (MTMF) partial unmixing method. With this method, pixels with high MF scores and low MT scores were identified as candidate locations of possible unlawful buildings. A case study in the Mangshan Tombs, China demonstrated that this method had a better accuracy for identifying constructions than the commonly used fully-constrained linear unmixing model.

Copyright of Transactions of Beijing Institute of Technology is the property of Beijing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

MODIS time-series imagery is promising for generating regional and global land cover products. For Brazil, however, accurate fractional cropland covers (FCC) information is difficult to obtain due to frequent cloud coverage and the mixing-pixel problem. To address these problems, this study developed an innovative approach to map the FCC of the Mato Grosso State, Brazil through integrating linear spectral mixture analysis (LSMA) and seasonal dynamic index (SDI) models. With MOD13Q1 time-series EVI imagery, a seasonal dynamic index (SDI) was developed to represent the phenology of croplands. Furthermore, fractional land covers (e.g., vegetation, soil, and low albedo components) were derived with the LSMA algorithms. A stepwise regression model was established to estimate the FCC at the regional scale. Finally, ground truth cropland cover information was extracted from Landsat TM imagery using a hybrid method. Results indicated that the combination of multiple feature variables produced better results when compared with individual variables. Through cross-validation and comparative analysis, the coefficient of determination (R²) between the reference and estimated FCCs reached 0.84 with a Root Mean Square Error (RMSE) of 0.13. This indicates that the proposed method effectively improved the accuracy of fractional cropland mapping. When compared to the traditional per-pixel "hard" classification, the sub-pixel level maps illustrated detailed cropland spatial distribution patterns. [ABSTRACT FROM AUTHOR]

Hyperspectral remote sensing technology has become an important part of ground observation since the 1980s, and it is the main data source of information acquisition for ground objects. Hyperspectral image (HSIs) not only contains spatial information, but also contains abundant spectral information with tens to hundreds of contiguous spectral bands. The abundant spectral information of HSIs can help us better identify ground objects, which has greatly improved our ability to qualitatively and quantitatively sense the earth's surface. It has been intensively researched to make full use of both spatial and spectral information of HSIs, so as to accurately obtain the information of ground objects. This paper reviews quantum optimization algorithm-based hyperspectral image processing me-thods. The development and methodology of quantum optimization algorithm as well as its application in hyperspectral image processing are introduced. And some suggestion and expectation for further study of the quantum optimization algorithm-based hyperspectral image processing are given. [ABSTRACT FROM AUTHOR]

Mixed pixels commonly exist in low-resolution remote sensing images, and they are the key factors hindering the classification of land covers and high-precision mapping. To obtain the spatial information at the subpixel level, subpixel mapping (SPM) technologies, including the pixel-swapping algorithm (PSA), that use the unmixed proportions of various land covers and allocate subpixel land covers have been proposed. However, the PSA often falls into a local optimum solution. In this paper, we propose a SPM method, the PSA_MSA algorithm, that combines the PSA and the modified simulated annealing algorithm to find the global optimum solution. The modified simulated annealing algorithm swaps subpixels within a certain range to escape the local optimum solution. The method also optimizes all the mixed pixels in a randomized sequence to further improve the mapping accuracy. The experimental results demonstrate that the proposed PSA_MSA algorithm outperforms the existing PSA-based algorithms for SPM. The images with different spatial dependences are tested and the results show that the proposed algorithm is more suitable for images with high spatial autocorrelation. In addition, the effect of proportion error is analyzed by adding it in the experiments. The result shows that a higher proportion error rate leads to larger degradation of the subpixel mapping accuracy. Finally, the performance of PSA_MSA algorithm with different ranges of selection on subpixel-swapping is analyzed.

In this paper, a new joint spectral–spatial subpixel mapping model is proposed for hyperspectral remotely sensed imagery. Conventional approaches generally use an intermediate step based on the derivation of fractional abundance maps obtained after a spectral unmixing process, and thus the rich spectral information contained in the original hyperspectral data set may not be utilized fully. In this paper, a concept of subpixel abundance map, which calculates the abundance fraction of each subpixel to belong to a given class, was introduced. This allows us to directly connect the original (coarser) hyperspectral image with the final subpixel result. Furthermore, the proposed approach incorporates the spectral information contained in the original hyperspectral imagery and the concept of spatial dependence to generate a final subpixel mapping result. The proposed approach has been experimentally evaluated using both synthetic and real hyperspectral images, and the obtained results demonstrate that the method achieves better results when compared to other seven subpixel mapping methods. The numerical comparisons are based on different indexes such as the overall accuracy and the CPU time. Moreover, the obtained results are statistically significant at 95% confidence. [ABSTRACT FROM AUTHOR]

Owing to the limitation of spatial resolution of the imaging sensor and the variability of ground surfaces, mixed pixels are widesperead in hyperspectral imagery. The traditional subpixel mapping algorithms treat all mixed pixels as boundary-mixed pixels while ignoring the existence of linear subpixels. To solve this question, this paper proposed a new subpixel mapping method based on linear subpixel feature detection and object optimization. Firstly, the fraction value of each class is obtained by spectral unmixing. Secondly, the linear subpixel features are pre-determined based on the hyperspectral characteristics and the linear subpixel feature; the remaining mixed pixels are detected based on maximum linearization index analysis. The classes of linear subpixels are determined by using template matching method. Finally, the whole subpixel mapping results are iteratively optimized by binary particle swarm optimization algorithm. The performance of the proposed subpixel mapping method is evaluated via experiments based on simulated and real hyperspectral data sets. The experimental results demonstrate that the proposed method can improve the accuracy of subpixel mapping. [ABSTRACT FROM AUTHOR]

This letter investigates the use of coarse-image features for predicting class labels at a given finer spatial scale. In this regard, two unsupervised subpixel mapping approaches, a semivariogram method, and a pixel-affinity based method are proposed. Furthermore, segmentation-based spectral unmixing is explored so as to address the spectral variability and nonconvexity of classes. In addition, the gradient information is employed to resolve uncertainties in the unmixing process. The proposed modifications based on pixel-affinity and semivariogram have produced an accuracy improvement of 5% or more over the state-of-the-art approaches. [ABSTRACT FROM PUBLISHER]

The majority of future population growth in mountains will occur in small- and medium-sized cities and towns and affect vulnerable ecosystems. However, mountain settlements are often omitted from global land cover analyses due to the low spatial resolution of satellite images, which cannot resolve the small scale of mountains settlements. This study demonstrates, for the first time, the potential of deep learning to detect human settlements in mountains at the sub-pixel level, based on Landsat satellite imagery. We hypothesized that adding spatial and temporal features could improve the detection of mountain settlements since spectral information alone led to inaccurate results. For spatial features, we compared a U-shaped neural network (U-Net), a deep learning algorithm that automatically learns spatial features, with a simple random forest (RF) algorithm. Then, we assessed whether temporal features would increase accuracy by comparing two input datasets, multispectral imagery and temporal features from the Continuous Change Detection and Classification (CCDC) algorithm. We evaluated each method by calculating the accuracies of (1) the binary settlement footprint, (2) the subpixel estimates of impervious surfaces, and (3) urban growth. We tested the accuracies using visually interpreted datasets from time-series Google Earth images across the Hindu Kush Himalaya that were not used for training to evaluate model transferability. The U-Net successfully improved mountain settlement mapping compared to the random forest, with a substantial discrepancy in small settlements. The time-series results from the U-Net successfully captured long-term urban growth but fewer short-term changes. Contrary to expectations, the CCDC temporal features reduced the accuracy of mountain settlement mapping due to frequent cloud cover in hilly areas. Our subpixel analysis reveals that the built-up area of the Hindu Kush Himalaya has expanded at a rate of 61 km2 per year from 1990 to 2020, which is about twice the estimate of the Global Human Settlement Layer using binary urban/non-urban classifications. • CNN regression sucessfully detects subpixel small settlements in mountains. • We reveal two times more built-up areas in the Himalayas than existing estimates. • CNN substantially improves mountain settlement mapping compared to RF. • Temporal features (CCDC) did not improve mountain settlement mapping due to clouds. • CNN generates time series and captures urban growth in mountains. [ABSTRACT FROM AUTHOR]

Capturing the dynamics of a lake-water area using remotely sensed images has always been an essential task. Most of the fine spatial resolution data are unsuitable for this purpose because of their low temporal resolution and limited scene coverage. A Visible Infrared Imaging Radiometer Suite on board the Suomi National Polar-orbiting Partnership (Suomi NPP-VIIRS) is a newly-available and appropriate sensor for monitoring large lakes due to its frequent revisits and wide swath (more than 3000 km). However, it provides visible and infrared images at relatively coarse spatial resolutions, which would sometimes hamper the accurate mapping of lake shorelines. This study, therefore, proposes a two-step downscaling method that combines spectral unmixing and subpixel mapping to produce a finer resolution lake map from NPP-VIIRS imagery, which is then applied to delineate the shorelines of five plateau lakes in Yunnan Province, as well as the shoreline dynamics of Poyang Lake at three separate times. A newly published global water dynamic dataset is employed in this study to improve the downscaling method. Results suggest that the proposed method can generate a finer resolution lake map that exhibits more details of the shoreline than hard classification. The downscaling results of the Suomi NPP-VIIRS generally achieve higher than 75% accuracy, while the downscaling results of a Landsat-simulated fraction map could have accuracy higher than 85%. This reveals that errors and uncertainties exist in both procedures, but mainly come from the spectral unmixing procedure which retrieves water fractions from NPP-VIIRS data. [ABSTRACT FROM AUTHOR]

Generating synthetically mixed data from library spectra provides a direct means to train empirical regression models for subpixel mapping. In order to best represent the subpixel composition of image data, the generation of synthetic mixtures must incorporate a multitude of mixing possibilities. This can lead to an excessive amount of training samples. We show that increasing mixing complexity in the training set improves model performance when quantifying urban land cover with support vector regression (SVR). To cope with the challenging increase in the number of training samples, we propose the use of ensemble learning based on bootstrap aggregation from synthetically mixed training data. The workflow is tested on simulated spaceborne imaging spectrometer data acquired over Berlin, Germany. Comparisons to SVR without bagging and multiple endmember spectral mixture analysis reveal the usefulness of the methodology for quantitative urban mapping. [ABSTRACT FROM PUBLISHER]

Subpixel mapping techniques have been widely utilized to determine the spatial distribution of the different land-cover classes in mixed pixels at a subpixel scale by converting low-resolution fractional abundance maps (estimated by a linear mixture model) into a finer classification map. Over the past decades, many subpixel mapping algorithms have been proposed to tackle this problem. It has been obvious that the utilized abundance map has a strong impact on the subsequent subpixel mapping procedure. However, limited attention has been given to the impact of the different aspects in the spectral unmixing model on the subpixel mapping performance. In this paper, a detailed quantitative assessment of different aspects in linear spectral mixture analysis, such as the criteria used to determine the types of pixels, the abundance sum-to-one constraint in the unmixing, and the accuracy of the utilized abundance maps, is investigated. This is accomplished by designing an experimental procedure with replaceable components. A total of six hyperspectral images (four synthetic and two real) were utilized in our experiments. By investigating these critical issues, we can further improve the performance of subpixel mapping techniques. [ABSTRACT FROM PUBLISHER]

In this paper， an image sub-pixel mapping algorithm based on support vector machine (SVM)has been presented for hyper spectral imagery. Since the total variation (TV) model is classic Edge-preserving smoothing filter，the authors introduce this model as a presmoothing to improve at--curacies of spectral unmixing and sub-pixel mapping. A lso，according to the spatial correlation theory ， our algorithm not only considers the impact of the abundance for the current pixel on sub-pixel classitication' but also takes the effect of adjacent pixels into account. In addition，to improve the efficiency of our algorithm，we propose to decrease the number of samples by eliminating pure pixels during the training and testing procedure in supervised classitication. Experimental results on real-world hyper spectral remote sensing dataset show the validity of our algorithm on both visual inspection and quantitative analysis. [ABSTRACT FROM AUTHOR]

Water bodies are ubiquitous features in Arctic wetlands. Ponds, i.e., waters with a surface area smaller than 104 m2, have been recognized as hotspots of biological activity and greenhouse gas emissions but are not well inventoried. This study aimed to identify common characteristics of three Arctic wetlands including water body size and abundance for different spatial resolutions, and the potential of Landsat-5 TM satellite data to show the subpixel fraction of water cover (SWC) via the surface albedo. Water bodies were mapped using optical and radar satellite data with resolutions of 4mor better, Landsat-5 TM at 30mand the MODIS water mask (MOD44W) at 250m resolution. Study sites showed similar properties regarding water body distributions and scaling issues. Abundance-size distributions showed a curved pattern on a log-log scale with a flattened lower tail and an upper tail that appeared Paretian. Ponds represented 95% of the total water body number. Total number of water bodies decreased with coarser spatial resolutions. However, clusters of small water bodies were merged into single larger water bodies leading to local overestimation of water surface area. To assess the uncertainty of coarse-scale products, both surface water fraction and the water body size distribution should therefore be considered. Using Landsat surface albedo to estimate SWC across different terrain types including polygonal terrain and drained thermokarst basins proved to be a robust approach. However, the albedo–SWC relationship is site specific and needs to be tested in other Arctic regions. These findings present a baseline to better represent small water bodies of Arctic wet tundra environments in regional as well as global ecosystem and climate models.

Fractional green vegetation cover (FVC) is a useful parameter for many environmental and climate-related applications. A common approach for estimating FVC involves the linear unmixing of two spectral endmembers in a remote sensing image; bare soil and green vegetation. The spectral properties of these two endmembers are typically determined based on field measurements, estimated using additional data sources (e.g., soil databases or land cover maps), or extracted directly from the imagery. Most FVC estimation approaches do not consider that the spectral properties of endmembers may vary across space. However, due to local differences in climate, soil type, vegetation species, etc., the spectral characteristics of soil and green vegetation may exhibit positive spatial autocorrelation. When this is the case, it may be useful to take these local variations into account for estimating FVC. In this study, spatial interpolation (Inverse Distance Weighting and Ordinary Kriging) was used to predict variations in the spectral characteristics of bare soil and green vegetation across space. When the spatially-interpolated values were used in place of scene-invariant endmember values to estimate FVC in an Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) image, the accuracy of FVC estimates increased, providing evidence that it may be useful to consider the effects of spatial autocorrelation for spectral mixture analysis.

This letter presents a novel subpixel mapping method based on Markov random field (MRF) and graph cut optimization. First, the support vector regression is applied to generate the fractional images of classes based on randomly selected training pixels. Second, the spatially adaptive MRF-based subpixel mapping method is adopted to formulate the energy function. Third, to minimize the energy function, graph cut is applied. Finally, the subpixel vector border is extracted and integrated as a weighting function to fine-tune the smoothing parameters. We conduct the experiments on a downsampled SPOT-7 multispectral image and two synthetic images with regular and irregular objects, respectively. The results prove that graph cut can be an alternative method to the commonly used simulated annealing for the energy function optimization in MRF-based subpixel mapping, considering its much higher efficiency and comparable classification accuracy. Moreover, the integration of subpixel edge information is helpful to improve the accuracy of subpixel mapping results. [ABSTRACT FROM PUBLISHER]

Existing global land use/land cover (LULC) raster maps have limited spatial and thematic resolution relative to the strong heterogeneity of agricultural landscapes. One promising approach to derive more informative maps is using fractional cover instead of hard classification. Here, we evaluate the effect of three key data processing options on the performance of random forest (RF) fractional cover models for moderate resolution imaging spectroradiometer (MODIS) data in a heterogeneous agricultural landscape in a monsoon region: 1) selection of spectral predictor sets [normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), surface reflectance (SR), and all combined (Full)]; 2) time interval (8-day vs. 16-day); and 3) smoothing (no smoothing versus Savitzky–Golay (SG) filter). Model performance was assessed with spatially stratified root-mean-square error (RMSE), Spearman’s rank correlation, and $R^2$, per LULC type and averaged over all types. We found adequate performance of the best model (avg. $\rho= 0.62$) that used all predictors, 8-day interval and no smoothing. Among the different alternatives, the choice of predictors accounted for 36.3% of the variation, smoothing for 19.0%, and time interval for 17.9%. The intrinsic dimensionalities of the spectral predictors were investigated to complement the variable importance analyses. Although predicting LULC fractions for minor types remained difficult, our results suggest that existing satellite products can be a useful source of information about LULC at subpixel level provided the data-processing options are properly chosen. [ABSTRACT FROM PUBLISHER]

Subpixel mapping techniques aim to obtain the spatial location and distribution of subpixels by transforming the information coming from a set of input abundance maps into a classification result with higher spatial resolution. However, traditional subpixel mapping algorithms generally ignore the possible errors that are due to abundance estimation inaccuracies by spectral unmixing techniques. In this paper, we propose a new genetic algorithm-based subpixel mapping technique that solves the subpixel mapping problem by correcting the potential errors in the estimated abundance fractions used as input to the subpixel mapping process. The proposed algorithm has been compared with other two genetic subpixel mapping methods, using both synthetic and real hyperspectral images. Our experimental results demonstrate that the proposed approach outperforms traditional subpixel mapping algorithms, thus providing an effective option to improve the accuracy of subpixel mapping for remotely sensed hyperspectral images. [ABSTRACT FROM PUBLISHER]

Various subpixel mapping (SPM) methods have been proposed as downscaling techniques to reduce uncertainty in classifying mixed pixels. Such methods can provide category maps of a higher spatial resolution than the original input images. The aim of this study was to explore and validate the potential of SPM as an alternative method for obtaining land use/land cover (LULC) maps of regions where high-spatial-resolution LULC maps are unavailable. An experimental design was proposed to evaluate the feasibility of SPM for providing the alternative LULC maps. A case study was implemented in the Jingjinji region of China. SPM results for spatial resolutions of 500-100 m were derived from a single 1-km synthetic fraction image using two representative SPM methods. The 1-km synthetic fraction image was assumed to be error free. Accuracy assessment and analysis showed that overall accuracies of the SPM results were reduced from about 85% to 75% with increasing spatial resolution, and that producer's accuracies varied considerably from about 62% to 93%. SPM performed best when handling areal features in comparison with linear and point features. The highest accuracies were achieved for areas with the lowest complexity. The study concluded that the results from SPM could provide an alternative LULC data source with acceptable accuracy, especially in areas with low complexity and with a large proportion of areal features. [ABSTRACT FROM AUTHOR]

Subpixel mapping, which is a promising technique based on the assumption of spatial dependence, enhances the spatial resolution of images by dividing a mixed pixel into several subpixels and assigning each subpixel to a single land-cover class. The traditional subpixel mapping methods usually utilize the fractional abundance images obtained by a spectral unmixing technique as input and consider the spatial correlation information among pixels and subpixels. However, most of these algorithms treat subpixels separately and locally while ignoring the rationality of global patterns. In this paper, a novel subpixel mapping model based on sparse representation theory, namely, adaptive sparse subpixel mapping with a total variation model (ASSM-TV), is proposed to explore the possible spatial distribution patterns of subpixels by considering these subpixels as an integral patch. In this way, the proposed method can obtain the optimal subpixel mapping result by determining the most appropriate subpixel spatial pattern. However, the number of possible spatial configurations of subpixels can increase sharply with large-scale factors, and therefore, in ASSM-TV, the subpixel mapping is considered as a sparse representation problem. A preconstructed discrete cosine transform dictionary, which consists of piecewise smooth subpixel patches and textured patches, is utilized to express the original subpixel mapping observation in a sparse representation pattern. The total variation prior model is designed as a spatial regularization constraint to characterize the relationship between a subpixel and its neighboring subpixels. In addition, a joint maximum a posteriori model is proposed to adaptively select the regularization parameters. Compared with the other traditional and state-of-the-art subpixel mapping approaches, the experimental results using a simulated image, three synthetic hyperspectral remote sensing images, and two real remote sensing images demonstrate that the proposed algorithm can obtain better results, in both visual and quantitative evaluations. [ABSTRACT FROM PUBLISHER]

Subpixel mapping is a method of enhancing the spatial resolution of images, which involves dividing a mixed pixel into subpixels and assigning each subpixel to a definite land-cover class. Traditionally, subpixel mapping is based on the assumption of spatial dependence, and the spatial correlation information among pixels and subpixels is considered in the prediction of the spatial locations of land-cover classes within the mixed pixels. In this paper, a novel subpixel mapping method for hyperspectral remote sensing imagery based on a nonlocal method, namely nonlocal total variation subpixel mapping (NLTVSM), is proposed to use the nonlocal self-similarity prior to improve the performance of the subpixel mapping task. Differing from the existing spatial regularization subpixel mapping technique, in NLTVSM, the nonlocal total variation is used as a spatial regularizer to exploit the similar patterns and structures in the image. In this way, the proposed method can obtain an optimal subpixel mapping result and accuracy by considering the nonlocal spatial information. Compared with the classical and state-of-the-art subpixel mapping approaches, the experimental results using a simulated hyperspectral image, two synthetic hyperspectral remote sensing images, and a real hyperspectral image confirm that the proposed algorithm can obtain better results in both visual and quantitative evaluations. [ABSTRACT FROM AUTHOR]

The subpixel mapping technique can specify the spatial distribution of different categories at the subpixel scale by converting the abundance map into a higher resolution image, based on the assumption of spatial dependence. Traditional subpixel mapping algorithms only utilize the low-resolution image obtained by the classification image downsampling and do not consider the spectral unmixing error, which is difficult to account for in real applications. In this paper, to improve the accuracy of the subpixel mapping, an adaptive subpixel mapping method based on a maximum a posteriori (MAP) model and a winner-take-all class determination strategy, namely, AMCDSM, is proposed for hyperspectral remote sensing imagery. In AMCDSM, to better simulate a real remote sensing scene, the low-resolution abundance images are obtained by the spectral unmixing method from the downsampled original image or real low-resolution images. The MAP model is extended by considering the spatial prior models (Laplacian, total variation (TV), and bilateral TV) to obtain the high-resolution subpixel distribution map. To avoid the setting of the regularization parameter, an adaptive parameter selection method is designed to acquire the optimal subpixel mapping results. In addition, in AMCDSM, to take into account the spectral unmixing error in real applications, a winner-take-all strategy is proposed to achieve a better subpixel mapping result. The proposed method was tested on simulated, synthetic, and real hyperspectral images, and the experimental results demonstrate that the AMCDSM algorithm outperforms the traditional subpixel mapping methods and provides a simple and efficient algorithm to regularize the ill-posed subpixel mapping problem. [ABSTRACT FROM PUBLISHER]

The existence of mixed pixels is a major problem in remote-sensing image classification. Although the soft classification and spectral unmixing techniques can obtain an abundance of different classes in a pixel to solve the mixed pixel problem, the subpixel spatial attribution of the pixel will still be unknown. The subpixel mapping technique can effectively solve this problem by providing a fine-resolution map of class labels from coarser spectrally unmixed fraction images. However, most traditional subpixel mapping algorithms treat all mixed pixels as an identical type, either boundary-mixed pixel or linear subpixel, leading to incomplete and inaccurate results. To improve the subpixel mapping accuracy, this paper proposes an adaptive subpixel mapping framework based on a multiagent system for remote-sensing imagery. In the proposed multiagent subpixel mapping framework, three kinds of agents, namely, feature detection agents, subpixel mapping agents and decision agents, are designed to solve the subpixel mapping problem. Experiments with artificial images and synthetic remote-sensing images were performed to evaluate the performance of the proposed subpixel mapping algorithm in comparison with the hard classification method and other subpixel mapping algorithms: subpixel mapping based on a back-propagation neural network and the spatial attraction model. The experimental results indicate that the proposed algorithm outperforms the other two subpixel mapping algorithms in reconstructing the different structures in mixed pixels. [ABSTRACT FROM AUTHOR]

This paper presents a new subpixel mapping method based on subpixel attraction-repulsion. The proposed method is formulated as an optimization problem with respect to attraction-repulsion among subpixels and is used to reconstruct a finer spatial resolution image from a lower resolution one. A comprehensive experiment is conducted to demonstrate the performance of the proposed method, by comparing it with the other three existing subpixel mapping methods, i.e., linear optimization, pixel swapping and spatial attraction model methods. In the experiment, both a synthetic image with known fractional abundances and an EO-1 Hyperion hyperspectral image of Shanghai were used to evaluate performances of the subpixel mapping methods. The experimental result shows that by using spatial dependence with attraction between the same types of ground objects and repulsion between different types of these objects, the proposed subpixel mapping method achieves a better performance on subpixel mapping than the other three methods. [ABSTRACT FROM PUBLISHER]

This paper describes a hyperspectral image classification method to obtain classification maps at a finer resolution than the image's original resolution. We assume that a complementary color image of high spatial resolution is available. The proposed methodology consists of a soft classification procedure to obtain landcover fractions, followed by a subpixel mapping of these fractions. While the main contribution of this article is in fact the complete multisource framework for obtaining a subpixel map, the major novelty of this subpixel mapping approach is the inclusion of contextual information, obtained from the color image. Experiments, conducted on two hyperspectral images and one real multi source data set, show excellent results, when compared to classification of the hyperspectral data only. The advantage of the contextual approach, compared to conventional subpixel mapping approaches, is clearly demonstrated. [ABSTRACT FROM PUBLISHER]

Water bodies are ubiquitous features in Arctic wetlands. Ponds, i.e., waters with a surface area smaller than 104 m2, have been recognized as hotspots of biological activity and greenhouse gas emissions but are not well inventoried. This study aimed to identify common characteristics of three Arctic wetlands including water body size and abundance for different spatial resolutions, and the potential of Landsat-5 TM satellite data to show the subpixel fraction of water cover (SWC) via the surface albedo. Water bodies were mapped using optical and radar satellite data with resolutions of 4 m or better, Landsat-5 TM at 30 m and the MODIS water mask (MOD44W) at 250 m resolution. Study sites showed similar properties regarding water body distributions and scaling issues. Abundance-size distributions showed a curved pattern on a log-log scale with a flattened lower tail and an upper tail that appeared Paretian. Ponds represented 95% of the total water body number. Total number of water bodies decreased with coarser spatial resolutions. However, clusters of small water bodies were merged into single larger water bodies leading to local overestimation of water surface area. To assess the uncertainty of coarse-scale products, both surface water fraction and the water body size distribution should therefore be considered. Using Landsat surface albedo to estimate SWC across different terrain types including polygonal terrain and drained thermokarst basins proved to be a robust approach. However, the albedo-SWC relationship is site specific and needs to be tested in other Arctic regions. These findings present a baseline to better represent small water bodies of Arctic wet tundra environments in regional as well as global ecosystem and climate models. [ABSTRACT FROM AUTHOR]

In this paper, a novel subpixel mapping algorithm based on an adaptive differential evolution (DE) algorithm, namely, adaptive-DE subpixel mapping (ADESM), is developed to perform the subpixel mapping task for remote sensing images. Subpixel mapping may provide a fine-resolution map of class labels from coarser spectral unmixing fraction images, with the assumption of spatial dependence. In ADESM, to utilize DE, the subpixel mapping problem is transformed into an optimization problem by maximizing the spatial dependence index. The traditional DE algorithm is an efficient and powerful population-based stochastic global optimizer in continuous optimization problems, but it cannot be applied to the subpixel mapping problem in a discrete search space. In addition, it is not an easy task to properly set control parameters in DE. To avoid these problems, this paper utilizes an adaptive strategy without user-defined parameters, and a reversible-conversion strategy between continuous space and discrete space, to improve the classical DE algorithm. During the process of evolution, they are further improved by enhanced evolution operators, e.g., mutation, crossover, repair, exchange, insertion, and an effective local search to generate new candidate solutions. Experimental results using different types of remote images show that the ADESM algorithm consistently outperforms the previous subpixel mapping algorithms in all the experiments. Based on sensitivity analysis, ADESM, with its self-adaptive control parameter setting, is better than, or at least comparable to, the standard DE algorithm, when considering the accuracy of subpixel mapping, and hence provides an effective new approach to subpixel mapping for remote sensing imagery. [ABSTRACT FROM PUBLISHER]

Fractional green vegetation cover (FVC) is a useful parameter for many environmental and climate-related applications. A common approach for estimating FVC involves the linear unmixing of two spectral endmembers in a remote sensing image; bare soil and green vegetation. The spectral properties of these two endmembers are typically determined based on field measurements, estimated using additional data sources (e.g., soil databases or land cover maps), or extracted directly from the imagery. Most FVC estimation approaches do not consider that the spectral properties of endmembers may vary across space. However, due to local differences in climate, soil type, vegetation species, etc., the spectral characteristics of soil and green vegetation may exhibit positive spatial autocorrelation. When this is the case, it may be useful to take these local variations into account for estimating FVC. In this study, spatial interpolation (Inverse Distance Weighting and Ordinary Kriging) was used to predict variations in the spectral characteristics of bare soil and green vegetation across space. When the spatially-interpolated values were used in place of scene-invariant endmember values to estimate FVC in an Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) image, the accuracy of FVC estimates increased, providing evidence that it may be useful to consider the effects of spatial autocorrelation for spectral mixture analysis. [ABSTRACT FROM AUTHOR]

This paper forwards an advanced subpixel mapping algorithm to provide detailed information on the spatial distribution of land covers within a mixed pixel. This is achieved utilizing the area proportions of the endmember components a mixed pixel and its neighboring pixels. Fraction values, obtained through soft classification, are used to calculate the area ratios of the endmember components of the mixed pixel and neighboring pixels. After testing the algorithm with both artificial and synthetic images, the performance of the algorithm can be evaluated as being computationally efficient and accurate for obtaining comprehensive information on the spatial distribution of land covers. [ABSTRACT FROM AUTHOR]

Super-resolution land cover mapping aims at producing fine spatial resolution maps of land cover classes from a set of coarse-resolution class fractions derived from satellite information via, for example, spectral unmixing procedures. Based on a prior model of spatial structure or texture that encodes the expected patterns of classes at the fine (target) resolution, this paper presents a sequential simulation framework for generating alternative super-resolution maps of class labels that are consistent with the coarse class fractions. Two modes of encapsulating the prior structural information are investigated-one uses a set of indicator variogram models, and the other uses training images. A case study illustrates that both approaches lead to super-resolution class maps that exhibit a variety of spatial patterns ranging from simple to complex. Using four different examples, it is demonstrated that the structural model controls the patterns seen on the super-resolution maps, even for cases where the coarse fraction data are highly constraining. [ABSTRACT FROM AUTHOR]

Mixed pixels commonly exist in low-resolution remote sensing images, and they are the key factors hindering the classification of land covers and high-precision mapping. To obtain the spatial information at the subpixel level, subpixel mapping (SPM) technologies, including the pixel-swapping algorithm (PSA), that use the unmixed proportions of various land covers and allocate subpixel land covers have been proposed. However, the PSA often falls into a local optimum solution. In this paper, we propose a SPM method, the PSA_MSA algorithm, that combines the PSA and the modified simulated annealing algorithm to find the global optimum solution. The modified simulated annealing algorithm swaps subpixels within a certain range to escape the local optimum solution. The method also optimizes all the mixed pixels in a randomized sequence to further improve the mapping accuracy. The experimental results demonstrate that the proposed PSA_MSA algorithm outperforms the existing PSA-based algorithms for SPM. The images with different spatial dependences are tested and the results show that the proposed algorithm is more suitable for images with high spatial autocorrelation. In addition, the effect of proportion error is analyzed by adding it in the experiments. The result shows that a higher proportion error rate leads to larger degradation of the subpixel mapping accuracy. Finally, the performance of PSA_MSA algorithm with different ranges of selection on subpixel-swapping is analyzed. [ABSTRACT FROM AUTHOR]