Pub Date : 2016-08-01DOI: 10.1109/WHISPERS.2016.8071813
Weibo Ma, Kun Tan, Q. Du, Jianwei Ding, Qingwu Yan
The potential hazard of heavy metals in reclaimed mine soil has influenced on the human health. The inversion analysis of hyperspectral data can be used to estimate heavy metal content of the soil effectively. In this paper, the characteristic bands are extracted by spectral pretreatment, including Savitzky-Golay (SG), Standard Normal Variety (SNV), First Derivative (FD), Second Derivative (SD), or Continuum Removal (CR) etc. Then, the weighted k-Nearest Neighbor (weighted k-NN) method is applied in the heavy metal inversion modeling to estimate the content of heavy metal with hyperspectral data. Compared with the widely used partial least squares regression (PLS), support vector machine (SVM) and k-Nearest Neighbor method (k-NN), the experimental results shown that the accuracy of weighted k-NN method was higher than other methods in the inversion of heavy Zinc (Zn), Chromium (Cr) and Plumbum (Pb).
矿山复垦土壤中重金属的潜在危害已经影响到人体健康。利用高光谱数据的反演分析可以有效地估算土壤重金属含量。本文通过光谱预处理提取特征波段，包括Savitzky-Golay (SG)、Standard Normal Variety (SNV)、一阶导数(FD)、二阶导数(SD)、Continuum Removal (CR)等。然后，将加权k-最近邻(weighted k-NN)方法应用于重金属反演建模，利用高光谱数据估计重金属含量。实验结果表明，与广泛应用的偏最小二乘回归(PLS)、支持向量机(SVM)和k-最近邻方法(k-NN)相比，加权k-NN方法在重锌(Zn)、铬(Cr)和铅(Pb)反演中的精度高于其他方法。
{"title":"Estimating soil heavy metal concentration using hyperspectral data and weighted K-NN method","authors":"Weibo Ma, Kun Tan, Q. Du, Jianwei Ding, Qingwu Yan","doi":"10.1109/WHISPERS.2016.8071813","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071813","url":null,"abstract":"The potential hazard of heavy metals in reclaimed mine soil has influenced on the human health. The inversion analysis of hyperspectral data can be used to estimate heavy metal content of the soil effectively. In this paper, the characteristic bands are extracted by spectral pretreatment, including Savitzky-Golay (SG), Standard Normal Variety (SNV), First Derivative (FD), Second Derivative (SD), or Continuum Removal (CR) etc. Then, the weighted k-Nearest Neighbor (weighted k-NN) method is applied in the heavy metal inversion modeling to estimate the content of heavy metal with hyperspectral data. Compared with the widely used partial least squares regression (PLS), support vector machine (SVM) and k-Nearest Neighbor method (k-NN), the experimental results shown that the accuracy of weighted k-NN method was higher than other methods in the inversion of heavy Zinc (Zn), Chromium (Cr) and Plumbum (Pb).","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"16 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":"128142900","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.2016.8071732
D. Gillis
One of the biggest challenges in detecting underwater objects in hyperspectral imagery is that, unlike the land-based case, the observed spectrum of an underwater target is highly dependent on the properties of the surrounding water, as well as the depth of the target. In this paper we present a very general framework for underwater detection. The framework uses physics-based models to create a target space — the set of all observed spectra that a given target could generate for a given image. We then exploit the geometrical structure that is present in the target space to perform a nonlinear dimensionality reduction that greatly simplifies the detection problem. We also illustrate the framework with examples that use simulated targets at various depths.
{"title":"Detection of underwater objects in hyperspectral imagery","authors":"D. Gillis","doi":"10.1109/WHISPERS.2016.8071732","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071732","url":null,"abstract":"One of the biggest challenges in detecting underwater objects in hyperspectral imagery is that, unlike the land-based case, the observed spectrum of an underwater target is highly dependent on the properties of the surrounding water, as well as the depth of the target. In this paper we present a very general framework for underwater detection. The framework uses physics-based models to create a target space — the set of all observed spectra that a given target could generate for a given image. We then exploit the geometrical structure that is present in the target space to perform a nonlinear dimensionality reduction that greatly simplifies the detection problem. We also illustrate the framework with examples that use simulated targets at various depths.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"17 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":"128227006","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.2016.8071657
Jiangtao Peng, Lefei Zhang
In the joint sparse representation (JSR) model, a test pixel and its spatial neighbors are simultaneously approximated by a sparse linear combination of all training samples, and then the test pixel is classified based on the joint reconstruction residual of each class. Due to the least-squares representation of reconstruction residual, the JSR model is usually sensitive to outliers, such as background and noisy pixels. In order to eliminate the effect of noisy and outliers, we propose a robust correntropy-based JSR (CJSR) model for the hyperspectral image classification. It replaces the traditional square of the Euclidean distance to the correntropy-based metric in measuring the joint approximation error. To solve the correntropy-based joint sparsity model, a half-quadratic optimization technique is developed to convert the original non-convex and nonlinear optimization problem into an iteratively reweighted JSR problem. As a result, the optimization of our model can handle the noise in the spatial neighborhood of each test pixel. It can adaptively assign small weights to noisy pixels and put more emphasis on noise-free pixels. Experiments demonstrate the effectiveness of our model in comparison to the related state-of-the-art sparsity models.
{"title":"Correntropy-based robust joint sparse representation for hyperspectral image classification","authors":"Jiangtao Peng, Lefei Zhang","doi":"10.1109/WHISPERS.2016.8071657","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071657","url":null,"abstract":"In the joint sparse representation (JSR) model, a test pixel and its spatial neighbors are simultaneously approximated by a sparse linear combination of all training samples, and then the test pixel is classified based on the joint reconstruction residual of each class. Due to the least-squares representation of reconstruction residual, the JSR model is usually sensitive to outliers, such as background and noisy pixels. In order to eliminate the effect of noisy and outliers, we propose a robust correntropy-based JSR (CJSR) model for the hyperspectral image classification. It replaces the traditional square of the Euclidean distance to the correntropy-based metric in measuring the joint approximation error. To solve the correntropy-based joint sparsity model, a half-quadratic optimization technique is developed to convert the original non-convex and nonlinear optimization problem into an iteratively reweighted JSR problem. As a result, the optimization of our model can handle the noise in the spatial neighborhood of each test pixel. It can adaptively assign small weights to noisy pixels and put more emphasis on noise-free pixels. Experiments demonstrate the effectiveness of our model in comparison to the related state-of-the-art sparsity models.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"63 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":"132191831","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.2016.8071694
S. Nakhostin, N. Courty, Rémi Flamary, T. Corpetti
This paper is focused on spectral unmixing and present an original technique based on Optimal Transport. Optimal Transport consists in estimating a plan that transports a spectrum onto another with minimal cost, enabling to compute an associated distance (Wasserstein distance) that can be used as an alternative metric to compare hyperspectral data. This is exploited for spectral unmixing where abundances in each pixel are estimated on the basis of their projections in a Wasserstein sense (Bregman projections) onto known endmembers. In this work an over-complete dictionary is used to deal with internal variability between endmembers, while a regularization term, also based on Wasserstein distance, is used to promote prior proportion knowledge in the endmember groups. Experiments are performed on real hyperspectral data of asteroid 4-Vesta.
{"title":"Supervised planetary unmixing with optimal transport","authors":"S. Nakhostin, N. Courty, Rémi Flamary, T. Corpetti","doi":"10.1109/WHISPERS.2016.8071694","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071694","url":null,"abstract":"This paper is focused on spectral unmixing and present an original technique based on Optimal Transport. Optimal Transport consists in estimating a plan that transports a spectrum onto another with minimal cost, enabling to compute an associated distance (Wasserstein distance) that can be used as an alternative metric to compare hyperspectral data. This is exploited for spectral unmixing where abundances in each pixel are estimated on the basis of their projections in a Wasserstein sense (Bregman projections) onto known endmembers. In this work an over-complete dictionary is used to deal with internal variability between endmembers, while a regularization term, also based on Wasserstein distance, is used to promote prior proportion knowledge in the endmember groups. Experiments are performed on real hyperspectral data of asteroid 4-Vesta.","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":"125143305","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}
Hyperspectral images (HSIs) often suffer from various annoying degradations, which poses huge challenges for the practical applications. Fortunately, clean HSI is intrinsically low-rank, which opens up a broad category of HSI processing and analysis methods with high robustness against the complicated mixture of various noises and outliers. Based on the low rank property of HSI, this paper provides a comprehensive review on restoration, multiangle registration and unmixing methods for HSIs developed very recently, and insights for further investigations.
{"title":"Exploiting the low-rank property of hyperspectral imagery: A technical overview","authors":"Hongyan Zhang, Wei He, Wenzi Liao, Renbo Luo, Liangpei Zhang, A. Pižurica","doi":"10.1109/WHISPERS.2016.8071731","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071731","url":null,"abstract":"Hyperspectral images (HSIs) often suffer from various annoying degradations, which poses huge challenges for the practical applications. Fortunately, clean HSI is intrinsically low-rank, which opens up a broad category of HSI processing and analysis methods with high robustness against the complicated mixture of various noises and outliers. Based on the low rank property of HSI, this paper provides a comprehensive review on restoration, multiangle registration and unmixing methods for HSIs developed very recently, and insights for further investigations.","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":"129279793","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.2016.8071659
Xiong Zhou, A. Armitage, S. Prasad
Mapping and monitoring coastal wetlands and mangrove distributions as well as changes in cover help us better manage wetlands. The purpose of this study is to study the efficacy of airborne hyperspectral remote sensing to map and detect black mangroves (Avicennia germinans) in coastal wetlands in Galveston, TX. To overcome the scarcity of labeled mangrove data, superpixel segmentation is used to expand the limited training set for subsequent classification and detection. The spatial distributions of black mangrove are then predicted with a support vector machine (SVM) classifier. The presence of black mangrove is also tested with two standard target detection approaches, including modified generalized likelihood ratio test (GLRT), and constrained energy minimization (CEM). The experimental results indicate that the black mangrove species can be effectively distinguished using hyperspectral images, from other wetland vegetation and background classes while requiring very limited labeling effort.
{"title":"Mapping mangrove communities in coastal wetlands using airborne hyperspectral data","authors":"Xiong Zhou, A. Armitage, S. Prasad","doi":"10.1109/WHISPERS.2016.8071659","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071659","url":null,"abstract":"Mapping and monitoring coastal wetlands and mangrove distributions as well as changes in cover help us better manage wetlands. The purpose of this study is to study the efficacy of airborne hyperspectral remote sensing to map and detect black mangroves (Avicennia germinans) in coastal wetlands in Galveston, TX. To overcome the scarcity of labeled mangrove data, superpixel segmentation is used to expand the limited training set for subsequent classification and detection. The spatial distributions of black mangrove are then predicted with a support vector machine (SVM) classifier. The presence of black mangrove is also tested with two standard target detection approaches, including modified generalized likelihood ratio test (GLRT), and constrained energy minimization (CEM). The experimental results indicate that the black mangrove species can be effectively distinguished using hyperspectral images, from other wetland vegetation and background classes while requiring very limited labeling effort.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"139 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":"133859070","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.2016.8071660
D. Rosario, J. Romano
We examine for the first time in the scientific community the application of hyperspectral (HS) based anomaly detection in contrast to polarimetric (POL) based anomaly detection in the longwave infrared region of the spectrum, using a challenging dataset for the test that covers three diurnal cycles. For fairness, we standardized for both sensing modalities the characterization of the unknown background clutter through a repeated trial Binomial based random sampling approach, and attained in the process two new methods for anomaly detection. The POL method outperformed the HS method, especially in the most difficult time periods, between sunset and sunrise, by an average of 0.47 augmented performance.
{"title":"Hyperspectral-based verses polarimetric-based anomaly detection in the LWIR","authors":"D. Rosario, J. Romano","doi":"10.1109/WHISPERS.2016.8071660","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071660","url":null,"abstract":"We examine for the first time in the scientific community the application of hyperspectral (HS) based anomaly detection in contrast to polarimetric (POL) based anomaly detection in the longwave infrared region of the spectrum, using a challenging dataset for the test that covers three diurnal cycles. For fairness, we standardized for both sensing modalities the characterization of the unknown background clutter through a repeated trial Binomial based random sampling approach, and attained in the process two new methods for anomaly detection. The POL method outperformed the HS method, especially in the most difficult time periods, between sunset and sunrise, by an average of 0.47 augmented performance.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"60 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":"132432662","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.2016.8071766
Yongqiang Zhao, Chen Yi, Jingxiang Yang, J. Chan
Spectral information in hyperspectral imagery (HSI) directly acquired by sensors, commonly with surplus bands and redundant information, takes high memory and transmission costs, resulting in reduced spatial resolution and aggravated spectral mixture. Therefore, the desired high spectral resolution HSI can be obtained via spectral super-resolution after acquiring original HSI with lower spectral resolution but relatively higher spatial resolution. In this paper, we proposed a spectral super-resolution method based on spectral matrix factorization and dictionary learning. High and low spectral resolution HSIs are assumed to have the same spatial resolution and share the same spectral signatures. So abundances of low spectral resolution imagery can provide high spatial information, while its endmembers can supply accurate spectral characteristics. Then several high spectral resolution HSIs in 2-D forms are utilized to train a spectral dictionary which contains both high spatial resolution information and high spectral resolution information. Finally, the desired spectral enhancement results are achieved through the use of spatial fidelity constraint. Experiments on Sandigo dataset indicated the superiority of our proposed method.
{"title":"Spectral super-resolution based on matrix factorization and spectral dictionary","authors":"Yongqiang Zhao, Chen Yi, Jingxiang Yang, J. Chan","doi":"10.1109/WHISPERS.2016.8071766","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071766","url":null,"abstract":"Spectral information in hyperspectral imagery (HSI) directly acquired by sensors, commonly with surplus bands and redundant information, takes high memory and transmission costs, resulting in reduced spatial resolution and aggravated spectral mixture. Therefore, the desired high spectral resolution HSI can be obtained via spectral super-resolution after acquiring original HSI with lower spectral resolution but relatively higher spatial resolution. In this paper, we proposed a spectral super-resolution method based on spectral matrix factorization and dictionary learning. High and low spectral resolution HSIs are assumed to have the same spatial resolution and share the same spectral signatures. So abundances of low spectral resolution imagery can provide high spatial information, while its endmembers can supply accurate spectral characteristics. Then several high spectral resolution HSIs in 2-D forms are utilized to train a spectral dictionary which contains both high spatial resolution information and high spectral resolution information. Finally, the desired spectral enhancement results are achieved through the use of spatial fidelity constraint. Experiments on Sandigo dataset indicated the superiority of our proposed method.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"10 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":"121555173","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.2016.8071701
Junshu Wang, Guoming Zhang, Min Cao, Nan Jiang
The contradiction between high dimensional data and limited training samples is the main problem in hyperspectral remote sensing images classification. How to obtain high classification accuracy with limited labeled samples is an urgent issue. We propose a semisupervised classification algorithm SSP_EMP for hyperspectral remote sensing images based on spectral and spatial information. The spatial information is extracted by building extended morphological profiles (EMP) based on principle components of hyperspectral image. Utilize spectral and EMP from two view to enrich knowledge, and integrate the useful information of unlabeled data at the most extent to optimize the classifier. Pick high confident samples to augment training set and retrain the classifier. This process is performed iteratively. The proposed algorithm is tested on AVIRIS Indian Pines. Experimental results show significant improvements in terms of accuracy and kappa coefficient compared with the classification results based on spectral, EMP and the combination of spectral and EMP.
{"title":"Semi-supervised classification of hyperspectral image based on spectral and extended morphological profiles","authors":"Junshu Wang, Guoming Zhang, Min Cao, Nan Jiang","doi":"10.1109/WHISPERS.2016.8071701","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071701","url":null,"abstract":"The contradiction between high dimensional data and limited training samples is the main problem in hyperspectral remote sensing images classification. How to obtain high classification accuracy with limited labeled samples is an urgent issue. We propose a semisupervised classification algorithm SSP_EMP for hyperspectral remote sensing images based on spectral and spatial information. The spatial information is extracted by building extended morphological profiles (EMP) based on principle components of hyperspectral image. Utilize spectral and EMP from two view to enrich knowledge, and integrate the useful information of unlabeled data at the most extent to optimize the classifier. Pick high confident samples to augment training set and retrain the classifier. This process is performed iteratively. The proposed algorithm is tested on AVIRIS Indian Pines. Experimental results show significant improvements in terms of accuracy and kappa coefficient compared with the classification results based on spectral, EMP and the combination of spectral and EMP.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"102 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":"123582540","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.2016.8071772
Xing Zhang, G. Wen, Bingwei Hui, Wei Dai
The aim of segmentation is to partition the image into a set of adjacent homogeneous regions. Most of existing hyperspectral imagery (HSI) segmentation approaches were designed to assign each pixel to one of the regions. However, due to the low-spatial-resolution, pixel mixing presents a challenge for HSI segmentation because a mixed spectrum does not correspond to any single well-defined material. As a result, it is difficult to determine which region the mixed pixels belong to. To address such problem, we proposed a batch-wise segmentation algorithm for HSI. First, pure pixels and mixed pixels in the HSI are separated. Then, those pure pixels are grouped into different regions. Finally, the mixed pixels are determined by its spatial neighboring pure pixels. Experimental results on a real HSI data indicate that the proposed algorithm provides more accurate segmentation maps, when compared to the traditional segmentation techniques.
{"title":"A batch-wise segmentation algorithm for hyperspectral images","authors":"Xing Zhang, G. Wen, Bingwei Hui, Wei Dai","doi":"10.1109/WHISPERS.2016.8071772","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071772","url":null,"abstract":"The aim of segmentation is to partition the image into a set of adjacent homogeneous regions. Most of existing hyperspectral imagery (HSI) segmentation approaches were designed to assign each pixel to one of the regions. However, due to the low-spatial-resolution, pixel mixing presents a challenge for HSI segmentation because a mixed spectrum does not correspond to any single well-defined material. As a result, it is difficult to determine which region the mixed pixels belong to. To address such problem, we proposed a batch-wise segmentation algorithm for HSI. First, pure pixels and mixed pixels in the HSI are separated. Then, those pure pixels are grouped into different regions. Finally, the mixed pixels are determined by its spatial neighboring pure pixels. Experimental results on a real HSI data indicate that the proposed algorithm provides more accurate segmentation maps, when compared to the traditional segmentation techniques.","PeriodicalId":369281,"journal":{"name":"2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)","volume":"75 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":"124736936","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：