Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071708
A. Koz, Akin Caliskan, Aydin Alatan
Previously proposed hyperspectral image registration methods mostly focus on the registration of the images including overlapping bands in VNIR and SWIR range. In contrary to previous methods, we investigate the registration of hyperspectral images with no-overlapping bands in MWIR and LWIR range in this paper. The proposed approach achieves the image registration over 2D maps extracted from 3D hyperspectral data cubes. Considering that the main component of the captured signal in MWIR-LWIR range is thermal radiation, we first propose to use the brightness-temperature estimate of hyperspectral pixels to form the 2D image. In addition, hyperspectral pixel energy, average emissivity and the first three components of principal component analysis (PCA) transform are also utilized and tested for 3D-2D conversion. The performance of the methods are evaluated by the matching ratio of the interest points and by generating mosaic images from the given maps. The experimental results indicate that brightness-temperature estimate, pixel energy and first principal component gives comparable results for image matching. The emissivity maps and the remaining principal components are found to be not successful for image registration as these features do not form a common base for different band signals.
{"title":"Registration of MWIR-LWIR band hyperspectral images","authors":"A. Koz, Akin Caliskan, Aydin Alatan","doi":"10.1109/WHISPERS.2016.8071708","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071708","url":null,"abstract":"Previously proposed hyperspectral image registration methods mostly focus on the registration of the images including overlapping bands in VNIR and SWIR range. In contrary to previous methods, we investigate the registration of hyperspectral images with no-overlapping bands in MWIR and LWIR range in this paper. The proposed approach achieves the image registration over 2D maps extracted from 3D hyperspectral data cubes. Considering that the main component of the captured signal in MWIR-LWIR range is thermal radiation, we first propose to use the brightness-temperature estimate of hyperspectral pixels to form the 2D image. In addition, hyperspectral pixel energy, average emissivity and the first three components of principal component analysis (PCA) transform are also utilized and tested for 3D-2D conversion. The performance of the methods are evaluated by the matching ratio of the interest points and by generating mosaic images from the given maps. The experimental results indicate that brightness-temperature estimate, pixel energy and first principal component gives comparable results for image matching. The emissivity maps and the remaining principal components are found to be not successful for image registration as these features do not form a common base for different band signals.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123390127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071800
Utsav B. Gewali, S. Monteiro
Statistical models have been successful in accurately estimating the biochemical contents of vegetation from the reflectance spectra. However, their performance deteriorates when there is a scarcity of sizable amount of ground truth data for modeling the complex nonlinear relationship occurring between the spectrum and the biochemical quantity. We propose a novel Gaussian process based multitask learning method for improving the prediction of a biochemical through the transfer of knowledge from the learned models for predicting related biochemicals. This method is most advantageous when there are few ground truth data for the biochemical of interest, but plenty of ground truth data for related biochemicals. The proposed multitask Gaussian process hypothesizes that the inter-relationship between the biochemical quantities is better modeled by using a combination of two or more covariance functions and inter-task correlation matrices. In the experiments, our method outperformed the current methods on two real-world datasets.
{"title":"Multitask learning of vegetation biochemistry from hyperspectral data","authors":"Utsav B. Gewali, S. Monteiro","doi":"10.1109/WHISPERS.2016.8071800","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071800","url":null,"abstract":"Statistical models have been successful in accurately estimating the biochemical contents of vegetation from the reflectance spectra. However, their performance deteriorates when there is a scarcity of sizable amount of ground truth data for modeling the complex nonlinear relationship occurring between the spectrum and the biochemical quantity. We propose a novel Gaussian process based multitask learning method for improving the prediction of a biochemical through the transfer of knowledge from the learned models for predicting related biochemicals. This method is most advantageous when there are few ground truth data for the biochemical of interest, but plenty of ground truth data for related biochemicals. The proposed multitask Gaussian process hypothesizes that the inter-relationship between the biochemical quantities is better modeled by using a combination of two or more covariance functions and inter-task correlation matrices. In the experiments, our method outperformed the current methods on two real-world datasets.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123532779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071745
M. Colom, G. Blanchet, A. Klonecki, O. Lezeaux, E. Pequignot, F. Poustomis, C. Thiebaut, S. Ythier, J. Morel
We propose a new denoising method for 3D hyperspectral images for the future MetOp-Second Generation series satellite incorporating the new IASI-NG interferometer, to be launched in 2021. This adaptive method retrieves the data model directly from the input noisy granule, using the following techniques: dual clustering (spectral and spatial), dimensionality reduction by adaptive PCA, and Bayesian denoising. The use of dimensionality reduction by PCA has been already proven an effective denoising technique because of intrinsic data redundancy. We demonstrate here that by combining a local PCA dimensionality reduction with a dual clustering and a Bayesian denoising, it is possible to improve significantly the PSNR with respect to PCA reduction alone. This noise reduction hints at the possibility to multiply of the resolution of the satellite by factor 4, while keeping an acceptable SNR.
{"title":"BBD: A new Bayesian bi-clustering denoising algorithm for IASI-NG hyperspectral images","authors":"M. Colom, G. Blanchet, A. Klonecki, O. Lezeaux, E. Pequignot, F. Poustomis, C. Thiebaut, S. Ythier, J. Morel","doi":"10.1109/WHISPERS.2016.8071745","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071745","url":null,"abstract":"We propose a new denoising method for 3D hyperspectral images for the future MetOp-Second Generation series satellite incorporating the new IASI-NG interferometer, to be launched in 2021. This adaptive method retrieves the data model directly from the input noisy granule, using the following techniques: dual clustering (spectral and spatial), dimensionality reduction by adaptive PCA, and Bayesian denoising. The use of dimensionality reduction by PCA has been already proven an effective denoising technique because of intrinsic data redundancy. We demonstrate here that by combining a local PCA dimensionality reduction with a dual clustering and a Bayesian denoising, it is possible to improve significantly the PSNR with respect to PCA reduction alone. This noise reduction hints at the possibility to multiply of the resolution of the satellite by factor 4, while keeping an acceptable SNR.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071704
A. Saranathan, M. Parente
Hyperspectral images often contain multiple intimate (nonlinear) mixtures. When attempting to unmix such datasets it is important to identify (cluster) the different mixtures present in the data and also minimize the effects of the nonlinearities in the data due to intimate mixing (embedding). Manifold clustering and embedding techniques appear to be an ideal tool for this task. Previous work in the field of manifold clustering either make simplifying assumptions or trade-off the embedding objective to improve the clustering. This is unacceptable in the case of unmixing as the embedded data is used for future processing (for e.g. abundance estimation). We discuss a low rank neighborhood representation which expresses each point as an affine combination of its neighbors on the same manifold. This ensures that the reconstruction matrix has a block diagonal structure, enabling the identification of classes by spectral clustering. The embedding of the different manifolds can also be obtained from this matrix. We will show the improved performance of this algorithm on simulated as well as real hyperspectral reflectance data of two ternary mixtures with two shared endmembers.
{"title":"Unmixing multiple intimate mixtures via a locally low-rank representation","authors":"A. Saranathan, M. Parente","doi":"10.1109/WHISPERS.2016.8071704","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071704","url":null,"abstract":"Hyperspectral images often contain multiple intimate (nonlinear) mixtures. When attempting to unmix such datasets it is important to identify (cluster) the different mixtures present in the data and also minimize the effects of the nonlinearities in the data due to intimate mixing (embedding). Manifold clustering and embedding techniques appear to be an ideal tool for this task. Previous work in the field of manifold clustering either make simplifying assumptions or trade-off the embedding objective to improve the clustering. This is unacceptable in the case of unmixing as the embedded data is used for future processing (for e.g. abundance estimation). We discuss a low rank neighborhood representation which expresses each point as an affine combination of its neighbors on the same manifold. This ensures that the reconstruction matrix has a block diagonal structure, enabling the identification of classes by spectral clustering. The embedding of the different manifolds can also be obtained from this matrix. We will show the improved performance of this algorithm on simulated as well as real hyperspectral reflectance data of two ternary mixtures with two shared endmembers.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130987624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071741
L. Xuan, Z. Ye, Junping Zhang
This paper presented a new approach called bi-inverted Gaussian model to calculated the diagnostic characteristic parameters of vegetation spectral. And used the parameters calculated from Hyperion image to make water content mapping. Using laboratory experiment measuring data, the relationships between absorption depth and the vegetation water content (VWC) were calculated. between absorption depth and VWC was 0.868 and the RMSE was 0.798. The correlations between them were higher than other vegetation indices.
{"title":"Vegetation water content estimation using bi-inverted Gaussian model","authors":"L. Xuan, Z. Ye, Junping Zhang","doi":"10.1109/WHISPERS.2016.8071741","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071741","url":null,"abstract":"This paper presented a new approach called bi-inverted Gaussian model to calculated the diagnostic characteristic parameters of vegetation spectral. And used the parameters calculated from Hyperion image to make water content mapping. Using laboratory experiment measuring data, the relationships between absorption depth and the vegetation water content (VWC) were calculated. between absorption depth and VWC was 0.868 and the RMSE was 0.798. The correlations between them were higher than other vegetation indices.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125896823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071714
Mohammed Q. Alkhatib, M. Velez-Reyes
This paper presents a visual exploratory analysis of an AVIRIS hyperspectral image to understand the interactions between the spatial and spectral domains in hyperspectral unmixing. We show how the global data cloud may not be convex due to spatial constraints on the distribution of the materials in the scene. Furthermore, we show that by segmenting the data cloud in feature space into piecewise convex segments, we can analyze individual segments and extract endmembers that better capture local structures compared to methods that look at the global cloud. Challenges remain as to how to do the cloud segmentation using machine-based approaches. However, experimental results point to the use of segmentation as a way to address the problem.
{"title":"Understanding spatial-spectral domain interactions in hyperspectral unmixing using exploratory data analysis","authors":"Mohammed Q. Alkhatib, M. Velez-Reyes","doi":"10.1109/WHISPERS.2016.8071714","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071714","url":null,"abstract":"This paper presents a visual exploratory analysis of an AVIRIS hyperspectral image to understand the interactions between the spatial and spectral domains in hyperspectral unmixing. We show how the global data cloud may not be convex due to spatial constraints on the distribution of the materials in the scene. Furthermore, we show that by segmenting the data cloud in feature space into piecewise convex segments, we can analyze individual segments and extract endmembers that better capture local structures compared to methods that look at the global cloud. Challenges remain as to how to do the cloud segmentation using machine-based approaches. However, experimental results point to the use of segmentation as a way to address the problem.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"402 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127594903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071674
Jie Li, C. Qi, Jingping Zhu, Wenzi Liao, W. Philips
Hyperspectral imaging technique has been widely used in remote sensing, surveillance in agriculture, environmental monitoring, etc. However, spectral information alone cannot well discriminate objects made with the same material. Conventional methods either fuse complementary information from other sensors or mine relevant information from the original hyperspectral data to improve the recognition rations. It may increase the cost and reduce the efficiency. In this paper, we propose an easier alternative approach: we present the prototype of a compact static Fourier transform hyperspectral imaging polarimeter, which couples hyperspectraland polarization imaging in a unified instrument and allows better material discrimination. The instrument, which is formed by cascading two crystal retarders and a birefringent interferometer, offers significant advantages over traditional implementations. Specifically, without any internal moving parts or electronics controllable elements, the spectrum, full wavelength dependent polarization and spatial information of a scene can be acquired simultaneously. Principles and experimental results in a case study are encouraging.
{"title":"Static Fourier transform hyperspectral imaging polarimeter","authors":"Jie Li, C. Qi, Jingping Zhu, Wenzi Liao, W. Philips","doi":"10.1109/WHISPERS.2016.8071674","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071674","url":null,"abstract":"Hyperspectral imaging technique has been widely used in remote sensing, surveillance in agriculture, environmental monitoring, etc. However, spectral information alone cannot well discriminate objects made with the same material. Conventional methods either fuse complementary information from other sensors or mine relevant information from the original hyperspectral data to improve the recognition rations. It may increase the cost and reduce the efficiency. In this paper, we propose an easier alternative approach: we present the prototype of a compact static Fourier transform hyperspectral imaging polarimeter, which couples hyperspectraland polarization imaging in a unified instrument and allows better material discrimination. The instrument, which is formed by cascading two crystal retarders and a birefringent interferometer, offers significant advantages over traditional implementations. Specifically, without any internal moving parts or electronics controllable elements, the spectrum, full wavelength dependent polarization and spatial information of a scene can be acquired simultaneously. Principles and experimental results in a case study are encouraging.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128675375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071790
Lifu Zhang
A new software have been developed for multidimensional analysis for remote sensing application. A new data storage structure named “mdd” for storing long time series remotely sensed data with spatial, temporal and spectral dimensions was induced as well as. Five data formats were included within the multidimensional data storage, which were TSB, TSP, TIB, TIP and TIS. MARS can be used for building multidimensional datasets and extracting information from MDD data file for time-series analysis. This paper introduced the main functions of MARS software by using MODIS long time series data as an example. MARS have the potential on analyzing long time satellite datasets.
{"title":"Development of multidimensional analysis of remote sensing (MARS) software","authors":"Lifu Zhang","doi":"10.1109/WHISPERS.2016.8071790","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071790","url":null,"abstract":"A new software have been developed for multidimensional analysis for remote sensing application. A new data storage structure named “mdd” for storing long time series remotely sensed data with spatial, temporal and spectral dimensions was induced as well as. Five data formats were included within the multidimensional data storage, which were TSB, TSP, TIB, TIP and TIS. MARS can be used for building multidimensional datasets and extracting information from MDD data file for time-series analysis. This paper introduced the main functions of MARS software by using MODIS long time series data as an example. MARS have the potential on analyzing long time satellite datasets.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"1999 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116921266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071722
Daniele Picone, R. Restaino, G. Vivone, P. Addesso, M. Mura, J. Chanussot
The sharpening of hyperspectral (HS) images introduces novel questions that have never been faced by classical pansharpening, which deals with the fusion of multispectral and panchromatic images. In this paper, we focus on the fusion of high resolution MultiSpectral (MS) and low resolution HS data, namely tackling the problem of assigning the optimal MS channel for each HS band through the minimization of the Spectral Angle Mapper (SAM) metric. The performance is assessed on two datasets, both composed by a HS and a MS image acquired by the Hyperion and the ALI sensors, respectively. Several MultiResolution Analysis pansharpening approaches are used for evaluating the performance improvements with respect to existing methods.
{"title":"Multispectral and hyperspectral data fusion based on SAM minimization band assignment approach","authors":"Daniele Picone, R. Restaino, G. Vivone, P. Addesso, M. Mura, J. Chanussot","doi":"10.1109/WHISPERS.2016.8071722","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071722","url":null,"abstract":"The sharpening of hyperspectral (HS) images introduces novel questions that have never been faced by classical pansharpening, which deals with the fusion of multispectral and panchromatic images. In this paper, we focus on the fusion of high resolution MultiSpectral (MS) and low resolution HS data, namely tackling the problem of assigning the optimal MS channel for each HS band through the minimization of the Spectral Angle Mapper (SAM) metric. The performance is assessed on two datasets, both composed by a HS and a MS image acquired by the Hyperion and the ALI sensors, respectively. Several MultiResolution Analysis pansharpening approaches are used for evaluating the performance improvements with respect to existing methods.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117051721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071687
A. Karami, Rob Heylen, P. Scheunders
In this paper, we propose a new denoising method based on a 2D non-subsampled shearlet transform (NSST) and fully constrained least squares unmixing (FCLSU). In the proposed method, first low noisy (LN) bands are separated from high noisy (HN) bands using spectral correlation. Second, NSST is applied to each spectral band of the hyperspectral images. Third, LN bands are denoised using a thresholding technique on the shearlet coefficients and HN bands are denoised by applying FCLSU. The proposed method is compared to state of the art denoising methods on synthetic and real hyperspectral datasets. The effect of denoising on classification accuracy is also investigated. Obtained results show the superiority of the proposed approach.
{"title":"Denoising of hyperspectral images using shearlet transform and fully constrained least squares unmixing","authors":"A. Karami, Rob Heylen, P. Scheunders","doi":"10.1109/WHISPERS.2016.8071687","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071687","url":null,"abstract":"In this paper, we propose a new denoising method based on a 2D non-subsampled shearlet transform (NSST) and fully constrained least squares unmixing (FCLSU). In the proposed method, first low noisy (LN) bands are separated from high noisy (HN) bands using spectral correlation. Second, NSST is applied to each spectral band of the hyperspectral images. Third, LN bands are denoised using a thresholding technique on the shearlet coefficients and HN bands are denoised by applying FCLSU. The proposed method is compared to state of the art denoising methods on synthetic and real hyperspectral datasets. The effect of denoising on classification accuracy is also investigated. Obtained results show the superiority of the proposed approach.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114531470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：