Sub-pixel Mapping Research Articles

Pixel-level mapping method in high dynamic range imaging system based on DMD modulation

In order to build pixel-to-pixel correspondence between the CCD camera and digital micromirror device (DMD) in high dynamic range (HDR) imaging system, we proposed an absolute phase mapping method based on the first partial derivatives of phase-shifted composite fringes in this paper. Compared with the conventional phase mapping method, the needed fringe patterns of our method are reduced by one time, which improves the mapping efficiency. Meanwhile, experimental results show the proposed method has an accuracy improvement over the existing methods. The root mean square error is within 0.11 pixels in both the horizontal and vertical directions, reaching the sub-pixel mapping accuracy and indicating the superiority of our method. Finally, we combined the proposed mapping method with the imaging system and achieved high dynamic range imaging by photographing the surface of highlighted object, which verified the validity and practicability of our method.

Spatiotemporal Continuous Impervious Surface Mapping by Fusion of Landsat Time Series Data and Google Earth Imagery

The monitoring of impervious surfaces in urban areas using remote sensing with fine spatial and temporal resolutions is crucial for monitoring urban development and environmental changes in urban areas. Spatiotemporal super-resolution mapping (STSRM) fuses fine-spatial-coarse-temporal remote sensing data with coarse-spatial-fine-temporal data, allowing for urban impervious surface mapping at both fine-spatial and fine-temporal resolutions. The STSRM involves two main steps: unmixing the coarse-spatial-fine-temporal remote sensing data to class fraction images, and downscaling the fraction images to sub-pixel land cover maps. Yet, challenges exist in each step when applying STSRM in mapping impervious surfaces. First, the impervious surfaces have high spectral variability (i.e., high intra-class and low inter-class variability), which impacts the accurate extraction of sub-pixel scale impervious surface fractions. Second, downscaling the fraction images to sub-pixel land cover maps is an ill-posed problem and would bring great uncertainty and error in the predictions. This paper proposed a new Spatiotemporal Continuous Impervious Surface Mapping (STCISM) method to deal with these challenges in fusing Landsat and Google Earth imagery. The STCISM used the Multiple Endmember Spectral Mixture Analysis and the Fisher Discriminant Analysis to minimize the within-class variability and maximize the between-class variability to reduce the spectral unmixing uncertainty. In addition, the STCISM adopted a new temporal consistency check model to incorporate temporal contextual information to reduce the uncertainty in the time-series impervious surface prediction maps. Unlike the traditional temporal consistency check model that assumed the impervious-to-pervious conversion is unlikely to happen, the new model allowed the bidirectional conversions between pervious and impervious surfaces. The temporal consistency check was used as a post-procession method to correct the errors in the prediction maps. The proposed STCISM method was used to predict time-series impervious surface maps at 5 m resolution of Google Earth image at the Landsat frequency. The results showed that the proposed STCISM outperformed the STSRM model without using the temporal consistency check and the STSRM model using the temporal consistency check based on the unidirectional pervious-to-impervious surface conversion rule.

Integrating coarse-resolution images and agricultural statistics to generate sub-pixel crop type maps and reconciled area estimates

Reliable crop type maps are vital for agricultural monitoring, ensuring food security, and environmental sustainability assessments. Coarse-resolution imagery such as MODIS are widely used for crop type mapping due to their short revisit cycles, which is advantageous for detecting the seasonal dynamics of different crop types. However, the inherently low spatial resolution may restrict their utility for mapping crop types in regions with heterogeneous agricultural landscapes. Agricultural statistics, which provide crop acreage information at different spatial and temporal scales, have the potential to improve crop type mapping from remote sensing. Yet, previous studies have often used agricultural statistics as reference data to evaluate the accuracy of satellite-derived crop type maps but have rarely utilized them to improve crop type distribution mapping. The utility of integrating agricultural statistics with satellite images to produce high-accuracy crop type maps is rarely explored. This study presents a methodology for mapping sub-pixel crop type distributions via the integration of MODIS time series and agricultural statistics. We tested our approach in Heilongjiang Province, which has the highest agricultural production in China. First, we used an optimized random forest regression (RF-r) model with training samples derived from high spatial resolution images (i.e. SPOT and Landsat) to predict the sub-pixel crop type distributions from MODIS time series. To optimize the RF-r model, an 8-day MODIS time series of five vegetation indices in 2011 were used as the candidate independent variables, and a backward feature elimination strategy was implemented to select the best variables for model prediction. Second, we developed an Iterative Area Gap Spatial Allocation (IAGSA) method to spatially reconcile the discrepancies between the crop acreage estimated from MODIS-based maps and the agricultural statistics. We found that the MODIS-derived crop fractions agreed with those derived from the high-resolution images, with R2 > 0.75 for all crop types, yet there was a clear discrepancy between the crop acreage estimated from MODIS and agricultural statistics. The sub-pixel crop type maps adjusted by IAGSA were not only consistent with the agricultural statistics for crop acreage, but also retained the spatial distribution patterns of the original MODIS-derived crop fraction. Our results suggest the advantages of integrating coarse-resolution images and agricultural statistics to map sub-pixel crop type distributions, and to provide consistent estimation of crop acreage. The presented methodology has the potential to map large-scale crop type extent across regions in a cost-effective way.

Subpixel Change Detection Based on Radial Basis Function with Abundance Image Difference Measure for Remote Sensing Images

Recently, land cover change detection has become a research focus of remote sensing. To obtain the change information from remote sensing images at fine spatial and temporal resolutions, subpixel change detection is widely studied and applied. In this paper, a new subpixel change detection method based on radial basis function (RBF) for remote sensing images is proposed, in which the abundance image difference measure (AIDM) is designed and utilized to enhance the subpixel mapping (SPM) by borrowing the fine spatial distribution of the fine spatial resolution image to decrease the influence of the spectral unmixing error. First, the fine and coarse spatial resolution images are used to develop subpixel change detection. Second, linear spectral mixing modeling and the degradation procedure are conducted on the coarse and fine spatial resolution image to produce two temporal abundance images, respectively. Then, the designed AIDM is utilized to enhance the RBF-based SPM by comparing the two temporal abundance images. At last, the proposed RBF-AIDM method is applied for SPM and subpixel change detection. The synthetic images based on Landsat-7 Enhanced Thematic Mapper Plus (ETM+) and real case images based on two temporal Landsat-8 Operational Land Imager (OLI) images and one Moderate Resolution Imaging Spectroradiometer (MODIS) image are undertaken to validate the proposed method. The experimental results indicate that the proposed method can sufficiently decrease the influence of the spectral unmixing error and improve the subpixel change detection results.

Deep Subpixel Mapping Based on Semantic Information Modulated Network for Urban Land Use Mapping

Mixed pixel problem is omnipresent in remote sensing images for urban land use interpretation due to the hardware limitations. Subpixel mapping (SPM) is a usual way to solve this problem by improving the observation scale and realizing a finer spatial resolution land cover mapping. Recently, deep learning-based subpixel mapping network (DLSMNet) was proposed, benefited from its strong representation and learning ability, to restore a visually pleasing finer mapping. However, the spatial context features of artifacts are usually aggregated and progressively lost during the forward pass of the network without sufficient representation, which make it difficult to be learned and restored. In this article, a semantic information modulated (SIM) deep subpixel mapping network (SIMNet) is proposed, which uses low-resolution semantic images as prior, to reinforce the representation of spatial context features. In SIMNet, SIM module is proposed to parametrically incorporate the semantic prior into the state-of-the-art (SOTA) feed forward network architecture in an end-to-end training fashion. Furthermore, stacked SIM module with residual blocks (SIM_ResBlock) is adopted to pass the representation of spatial context feature to the deep layers, to get it fully learned during backpropagation. Experiments have been implemented on three public urban scenario data sets, and the SIMNet generates a clearer outline of artificial facilities with sufficient spatial context, and is distinctive for even individual building, which is challenging for other SOTA DLSMNet. The results demonstrate that the proposed SIMNet is a promising way for high-resolution urban land use mapping from easily available lower resolution remote sensing images.Mixed pixel problem is omnipresent in remote sensing images for urban land use interpretation due to the hardware limitations. Subpixel mapping (SPM) is a usual way to solve this problem by improving the observation scale and realizing a finer spatial resolution land cover mapping. Recently, deep learning-based subpixel mapping network (DLSMNet) was proposed, benefited from its strong representation and learning ability, to restore a visually pleasing finer mapping. However, the spatial context features of artifacts are usually aggregated and progressively lost during the forward pass of the network without sufficient representation, which make it difficult to be learned and restored. In this article, a semantic information modulated (SIM) deep subpixel mapping network (SIMNet) is proposed, which uses low-resolution semantic images as prior, to reinforce the representation of spatial context features. In SIMNet, SIM module is proposed to parametrically incorporate the semantic prior into the state-of-the-art (SOTA) feed forward network architecture in an end-to-end training fashion. Furthermore, stacked SIM module with residual blocks (SIM_ResBlock) is adopted to pass the representation of spatial context feature to the deep layers, to get it fully learned during backpropagation. Experiments have been implemented on three public urban scenario data sets, and the SIMNet generates a clearer outline of artificial facilities with sufficient spatial context, and is distinctive for even individual building, which is challenging for other SOTA DLSMNet. The results demonstrate that the proposed SIMNet is a promising way for high-resolution urban land use mapping from easily available lower resolution remote sensing images.

Generation of Sub-Pixel-Level Maps for Mixed Pixels in Hyperspectral Image Data

Hyperspectral data can find wide applications in classification and mapping of pure and mixed pixels in images of different land-cover types. Hyperspectral data of high spectral resolution enhance discrimination of target objects; but the low spatial resolution poses a challenge due to creation of mixed pixels. The cost of acquiring images at high resolution from sensors is high and rarely available. With images of coarser spatial resolution, it is difficult to identify the endmembers and their locations within the mixed pixel. This study utilizes the fractional abundance values of target endmembers obtained from linear spectral unmixing in locating the sub-pixels of a mixed pixel. The study illustrates the preparation of classified maps of finer spatial resolution by locating the sub-pixels through different mapping algorithms. A comparative analysis of these mapping algorithms, viz. attraction model-based sub-pixel mapping, simulated annealing, neighbourhood connectivity, cosine similarity-based mapping and Markov random fieldbased mapping has been made and an output generated. The algorithms have been implemented on standard hyperspectral datasets of Indian Pines having 200 spectral channels, Pavia University of 103 spectral channels and Jasper Ridge of 198 spectral channels. It has been observed that simulated annealing-based mapping produces higher accuracy rate than the other algorithms, whereas in terms of execution time, attraction model takes lesser time. The accuracy has been validated with the ground reference map of available standard hyperspectral datasets on which each algorithm has been tested and analysed.

Sub-Pixel Mapping Model Based on Total Variation Regularization and Learned Spatial Dictionary

In this research study, we deal with remote sensing data analysis over high dimensional space formed by hyperspectral images. This task is generally complex due to the large spectral, spatial richness, and mixed pixels. Thus, several spectral un-mixing methods have been proposed to discriminate mixing spectra by estimating the classes and their presence rates. However, information related to mixed pixel composition is very interesting for some applications, but it is insufficient for many others. Thus, it is necessary to have much more data about the spatial localization of the classes detected during the spectral un-mixing process. To solve the above-mentioned problem and specify the spatial location of the different land cover classes in the mixed pixel, sub-pixel mapping techniques were introduced. This manuscript presents a novel sub-pixel mapping process relying on K-SVD (K-singular value decomposition) learning and total variation as a spatial regularization parameter (SMKSVD-TV: Sub-pixel Mapping based on K-SVD dictionary learning and Total Variation). The proposed approach adopts total variation as a spatial regularization parameter, to make edges smooth, and a pre-constructed spatial dictionary with the K-SVD dictionary training algorithm to have more spatial configurations at the sub-pixel level. It was tested and validated with three real hyperspectral data. The experimental results reveal that the attributes obtained by utilizing a learned spatial dictionary with isotropic total variation allowed improving the classes sub-pixel spatial localization, while taking into account pre-learned spatial patterns. It is also clear that the K-SVD dictionary learning algorithm can be applied to construct a spatial dictionary, particularly for each data set.

Deep Convolutional Neural Network Framework for Subpixel Mapping

Subpixel mapping (SPM) is an effective way to solve the mixed pixel problem, which is a ubiquitous phenomenon in remotely sensed imagery, by characterizing subpixel distribution within the mixed pixels. In fact, the majority of the classical and state-of-the-art SPM algorithms can be viewed as a convolution process, but these methods rely heavily on fixed and handcrafted kernels that are insufficient in characterizing a geographically realistic distribution image. In addition, the traditional SPM approach is based on the prerequisite of abundance images derived from spectral unmixing (SU), during which process uncertainty inherently exists and is propagated to the SPM. In this article, a kernel-learnable convolutional neural network (CNN) framework for subpixel mapping (SPMCNN-F) is proposed. In SPMCNN-F, the kernel is learnable during the training stage based on the given training sample pairs of low- and high-resolution patches for learning a geographically realistic prior, instead of fixed priors. The end-to-end mapping structure enables direct subpixel information extraction from the original coarse image, avoiding the uncertainty propagation from the SU. In the experiments undertaken in this study, two state-of-the-art super-resolution networks were selected as application demonstrations of the proposed SPMCNN-F method. In experiment part, three hyperspectral image data sets were adopted, two in a synthetic coarse image approach and one in a real coarse image approach, for the validation. Additionally, a new data set with pairs of Moderate-resolution Imaging Spectroradiometer (MODIS) and Landsat images were adopted in a real coarse image approach, for further validation of SPMCNN-F in large-scale area. The restored fine distribution images obtained in all the experiments showed a perceptually better reconstruction quality, both qualitatively and quantitatively, confirming the superiority of the proposed SPM framework.

Day and night synergy to improve subpixel urban impervious surface mapping in desert environments at 30-m Landsat resolution

ABSTRACT Few studies provide effective guidance for detecting subpixel urban impervious surface in desert environments. Such an environmental setting is substantially different from the study areas of most existing studies, especially with complicated desert landforms. To improve the accuracy of subpixel mapping of urban impervious surface in desert environments, an integrative approach is proposed to estimate fractional urban impervious surface at the 30-m resolution. This is done by the synergistic use of open-source datasets taken from day and night that characterize different aspects of human activities at a different time of a day. We carefully analyse the performance of three methods with model input combinations from different sources, i.e. the day and night image synergy, daytime images only, and georectified night-time International Space Station (ISS) photographs only. Three major findings are concluded from the analyses. First, the collective usage of remote sensing images derived from day and night yields reasonable results in all desert cities and outperforms any single-source data for subpixel urban impervious surface mapping. Second, among all the input features from multiple data sources, night light variables have a higher contribution than other variables of daytime images for subpixel urban impervious surface mapping in desert cities, regardless of lighting types. Third, since desert cities remain understudied in previous studies, the proposed synergy method fills this gap in the literature. This data fusion of multi-source remotely sensed data is promising, which can be employed for better subpixel urban mapping in support of various environmental and socioeconomic applications in the future.

General solution to reduce the point spread function effect in subpixel mapping

The point spread function (PSF) effect is ubiquitous in remote sensing images and imposes a fundamental uncertainty on subpixel mapping (SPM). The crucial PSF effect has been neglected in existing SPM methods. This paper proposes a general model to reduce the PSF effect in SPM. The model is applicable to any SPM methods treating spectral unmixing as pre-processing. To demonstrate the advantages of the new technique it was necessary to develop a new approach for accuracy assessment of SPM. To-date, accuracy assessment for SPM has been limited to subpixel classification accuracy, ignoring the performance of reproducing spatial structure in downscaling. In this paper, a new accuracy index is proposed which considers SPM performances in classification and restoration of spatial structure simultaneously. Experimental results show that by considering the PSF effect, more accurate SPM results were produced and small-sized patches and elongated features were restored more satisfactorily. Moreover, using the novel accuracy index, the quantitative evaluation was found to be more consistent with visual evaluation. This paper, thus, addresses directly two of the longest standing challenges in SPM (i.e., the limitations of the PSF effect and accuracy assessment undertaken only on a subpixel-by-subpixel basis).

Spatial Attraction Models Coupled with Elman Neural Networks for Enhancing Sub-Pixel Urban Inundation Mapping

Urban flooding is one of the most costly and destructive natural hazards worldwide. Remote-sensing images with high temporal resolutions have been extensively applied to timely inundation monitoring, assessing and mapping, but are limited by their low spatial resolution. Sub-pixel mapping has drawn great attention among researchers worldwide and has demonstrated a promising potential of high-accuracy mapping of inundation. Aimed to boost sub-pixel urban inundation mapping (SUIM) from remote-sensing imagery, a new algorithm based on spatial attraction models and Elman neural networks (SAMENN) was developed and examined in this paper. The Elman neural networks (ENN)-based SUIM module was developed firstly. Then a normalized edge intensity index of mixed pixels was generated. Finally the algorithm of SAMENN-SUIM was constructed and implemented. Landsat 8 images of two cities of China, which experienced heavy floods, were used in the experiments. Compared to three traditional SUIM methods, SAMENN-SUIM attained higher mapping accuracy according not only to visual evaluations but also quantitative assessments. The effects of normalized edge intensity index threshold and neuron number of the hidden layer on accuracy of the SAMENN-SUIM algorithm were analyzed and discussed. The newly developed algorithm in this study made a positive contribution to advancing urban inundation mapping from remote-sensing images with medium-low spatial resolutions, and hence can favor urban flood monitoring and risk assessment.

Multiobjective Subpixel Mapping With Multiple Shifted Hyperspectral Images

Subpixel mapping (SPM) is a useful technique that can interpret the spatial distribution inside mixed pixels and produce a finer-resolution classification map for hyperspectral remote-sensing imagery. However, SPM is essentially an ill-posed problem that requires additional information to produce the unique solution. The limited information of a single image is insufficient to make the mapping problem well posed, whereas the complementary spatial information of multiple shifted images is able to reduce the uncertainty and generate an accurate map. The maximum $a$ posteriori model is a feasible way to incorporate auxiliary information for SPM with multiple shifted images, but it introduces a sensitive regularization parameter, which is difficult to preset. Furthermore, the fixed parameter in the iterations influences the incorporation of the multiple images and the spatial prior. In this article, to address these issues, a multiobjective SPM framework for use with multiple shifted hyperspectral images (MOMSM) is proposed. In the proposed algorithm, a multiobjective model consisting of two objective functions, i.e., data fidelity and spatial prior terms, is constructed to transform the SPM into a multiobjective optimization problem, to get rid of the sensitive regularization parameter. To simultaneously optimize the two objective functions, a multiobjective memetic algorithm with a local search operator and an adaptive global replacement strategy is proposed. The multiple images and spatial information can be dynamically fused and the optimal mapping solution with a good balance between the two objectives can be finally obtained. Experiments conducted on both synthetic and real data sets confirm that the proposed method outperforms the other tested SPM algorithms.

Mapping urban-rural gradients of settlements and vegetation at national scale using Sentinel-2 spectral-temporal metrics and regression-based unmixing with synthetic training data

The increasing impact of humans on land and ongoing global population growth requires an improved understanding of land cover (LC) and land use (LU) processes related to settlements. The heterogeneity of built-up areas and infrastructures as well as the importance of not only mapping, but also characterizing anthropogenic structures suggests using a sub-pixel mapping approach for analysing related LC from space. We implement a regression-based unmixing approach for mapping built-up surfaces and infrastructure, woody vegetation and non-woody vegetation for all of Germany and Austria at 10 m resolution to demonstrate the potential of sub-pixel mapping. We map LC fractions for one point in time, using all available Sentinel-2 data from 2017 and 2018 (<70% cloud cover). We combine the concept of synthetically mixed training data with statistical aggregations from spectral-temporal metrics (STM) derived from Sentinel-2 reflectance time series. We specifically examine how STM can be used for creating synthetically mixed training data. STM are known to facilitate large area mapping by being largely independent of image acquisition dates and inherently incorporate phenological information. Vegetation is an important part of settlements and time series information supports its mapping. Synthetically mixed training data facilitates a streamlined training by using pure reference spectra to generate artificial mixtures as input to regression modelling of LC fractions in mixed pixels. We here show how combining both offers great potential for wall-to-wall LC fraction mapping. We further investigate the positive effect of STM on map results by comparing the performance of different subsets of STM combinations. Our results indicate that many STM combinations containing spectral variability and vegetation indices provide suitable input to creating synthetic training data for regression-based fraction mapping. Results for built-up surfaces and infrastructure (MAE 0.13/RMSE 0.18 at 20 m resolution), woody vegetation (0.18, 0.22) and non-woody vegetation (0.14, 0.19) are highly consistent across Germany and Austria. Only a few surface types were not accurately predicted in our nation-wide mapping. Further research is required to optimize mapping of temporally invariant bare soil and rock surfaces that show spectral similarity to built-up surfaces and infrastructure. The proposed methodology combines benefits of both regression-based modelling with synthetically mixed training data and STM, and thus facilitates mapping of LC fractions on a national scale and at high resolution. Such information will allow to better characterize settlements and identifying processes such as densification that are best represented by continuous LC mapping.

Sub-pixel mapping with point constraints

Remote sensing images contain abundant land cover information. Due to the complex nature of land cover, however, mixed pixels exist widely in remote sensing images. Sub-pixel mapping (SPM) is a technique for predicting the spatial distribution of land cover classes within mixed pixels. As an ill-posed inverse problem, the uncertainty of prediction cannot be eliminated and hinders the production of accurate sub-pixel maps. In contrast to conventional methods that use continuous geospatial information (e.g., images) to enhance SPM, in this paper, a SPM method with point constraints into SPM is proposed. The method of fusing point constraints is implemented based on the pixel swapping algorithm (PSA) and utilizes the auxiliary point information to reduce the uncertainty in the SPM process and increase map accuracy. The point data are incorporated into both the initialization and optimization processes of PSA. Experiments were performed on three images to validate the proposed method. The influences of the performances were also investigated under different numbers of point data, different spatial characters of land cover and different zoom factors. The results show that by using the point data, the proposed SPM method can separate more small-sized targets from aggregated artifacts and the accuracies are increased obviously. The proposed method is also more accurate than the advanced radial basis function interpolation-based method. The advantage of using point data is more evident when the point data size and scale factor are large and the spatial autocorrelation of the land cover is small. As the amount of point data increases, however, the increase in accuracy becomes less noticeable. Furthermore, the SPM accuracy can still be increased even if the point data and coarse proportions contain errors.

Optimized calibration method for ultra-field dual bands cameras based on thermal radiation checkerboard

Camera calibration is a vital and important work for machine vision. In the paper, an optimized calibration method for ultra-field dual bands cameras is proposed, which is based on the designed thermal radiation checkerboard. The optimizations are achieved in subpixel location, center location and mapping relationship, respectively. Specifically, the subpixel corner is located by performing the designed variable quadrilateral template on edge gradients and calculating their minimum orthogonal value. Then, the center location is accomplished through Gaussian fitting, in which the bottom point is taken as the potential center in iterations. Moreover, the RBF network is employed to replace the polynomial fitting and fit the mapping relationship between the camera coordinates and sensor coordinates. Thus, the accuracy of the mapping is increased, which contributes to the optimization of the intrinsic and extrinsic parameters. The experiments results show that the average root mean square error of the reprojection is reduced by nearly 50%. The calibrated parameters are accurate and have physical significance in the proposed calibration scheme.

Subpixel Mapping of Surface Water in the Tibetan Plateau with MODIS Data

This article presents a comprehensive subpixel water mapping algorithm to automatically produce routinely open water fraction maps in the Tibetan Plateau (TP) with the Moderate Resolution Imaging Spectroradiometer (MODIS). A multi-index threshold endmember extraction method was applied to select the endmembers from MODIS images. To incorporate endmember variability, an endmember selection strategy, called the combined use of typical and neighboring endmembers, was adopted in multiple endmember spectral mixture analysis (MESMA), which can assure a robust subpixel water fractions estimation. The accuracy of the algorithm was assessed at both the local scale and regional scale. At the local scale, a comparison using the eight pairs of MODIS/Landsat 8 Operational Land Imager (OLI) water maps demonstrated that subpixels water fractions were well retrieved with a root mean square error (RMSE) of 7.86% and determination coefficient (R2) of 0.98. At the regional scale, the MODIS water fraction map in October 2014 matches well with the TP lake data set and the Global Lake and Wetland Database (GLWD) in both latitudinal and longitudinal distribution. The lake area estimation is more consistent with the reference TP lake data set (difference of −3.15%) than the MODIS Land Water Mask (MOD44W) (difference of −6.39%).

Combining Pixel Swapping and Simulated Annealing for Land Cover Mapping.

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.

Sub-pixel Mapping of Copper- and Iron-Bearing Metamorphic Rocks Using ASTER Data: A Case Study of Toutak and Surian Complexes, NE Shiraz, Iran

Metamorphic rock units of Toutak and Surian complexes located in the Sanandaj–Sirjan metamorphic zone, NE Shiraz, Iran, were mapped using the matched filtering (MF) method on the visible near-infrared (VNIR) and shortwave infrared (SWIR) bands of advanced spaceborne thermal emission and reflection radiometer (ASTER) sensor. These complexes host magnetite and Cu–Zn–Ag volcanogenic massive sulfide (VMS) deposits. Mixed pixels of lithologic–mineralogic indicators of these deposits were detected to identify the prospecting areas. The spectra of end-members were extracted from imagery using sequential maximum angle convex cone (SMACC) model and were compared to the field and laboratory spectra to examine their characteristics. The key minerals including chlorite + epidote (greenschist), muscovite + biotite (mica schist), calcite + dolomite (marble), and muscovite + oligoclase (gneiss) were identified and were input to the algorithm for estimating the sub-pixel fractions of desired minerals. A generalized map of lithologies was then produced by combining the fraction maps of greenschist, mica schist, marble, and gneiss using a GIS. Finally, this lithologic association was applied to define the prospecting areas. The accuracy of results was assessed using R2 coefficient, field observations, and XRD analysis. The R2 coefficient was 0.74 for greenschist, 0.63 for mica schist, 0.65 for marble, and 0.53 for gneiss. The results also showed good agreement with field evidence, and thus, they can be used for finding potential targets for copper and iron deposits.

Unsupervised Bayesian Subpixel Mapping of Hyperspectral Imagery Based on Band-Weighted Discrete Spectral Mixture Model and Markov Random Field

Although accurate training and initialization information is difficult to acquire, unsupervised hyperspectral subpixel mapping (SPM) without relying on this predefined information is an insufficiently addressed research issue. This letter presents a novel Bayesian approach for unsupervised SPM of hyperspectral imagery (HSI) based on the Markov random field (MRF) and a band-weighted discrete spectral mixture model (BDSMM), with the following key characteristics. First, this is an unsupervised approach that allows adjustment of abundance and endmember information adaptively for less relying on algorithm initialization. Second, this approach consists of the BDSMM for accommodating the noise heterogeneity and the hidden label field of subpixels in HSI. The BDSMM also integrates SPM into the spectral mixture analysis and allows enhanced SPM by fully exploring the endmember-abundance patterns in HSI. Third, the MRF and BDSMM are integrated into a Bayesian framework to use both the spatial and spectral information efficiently, and an expectation-maximization (EM) approach is designed to solve the model by iteratively estimating the endmembers and the label field. Experiments on both simulated and real HSI demonstrate that the proposed algorithm can yield better performance than traditional methods.

Spatio-Temporal Sub-Pixel Land Cover Mapping of Remote Sensing Imagery Using Spatial Distribution Information From Same-Class Pixels

The generation of land cover maps with both fine spatial and temporal resolution would aid the monitoring of change on the Earth’s surface. Spatio-temporal sub-pixel land cover mapping (STSPM) uses a few fine spatial resolution (FR) maps and a time series of coarse spatial resolution (CR) remote sensing images as input to generate FR land cover maps with a temporal frequency of the CR data set. Traditional STSPM selects spatially adjacent FR pixels within a local window as neighborhoods to model the land cover spatial dependence, which can be a source of error and uncertainty in the maps generated by the analysis. This paper proposes a new STSPM using FR remote sensing images that pre- and/or post-date the CR image as ancillary data to enhance the quality of the FR map outputs. Spectrally similar pixels within the locality of a target FR pixel in the ancillary data are likely to represent the same land cover class and hence such same-class pixels can provide spatial information to aid the analysis. Experimental results showed that the proposed STSPM predicted land cover maps more accurately than two comparative state-of-the-art STSPM algorithms.