2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing最新文献_第7页

A vector SIFT operator for interest point detection in hyperspectral imagery 用于高光谱图像兴趣点检测的矢量SIFT算子

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594965

Leidy P. Dorado-Muñoz, M. Velez-Reyes, A. Mukherjee, B. Roysam

{"title":"A vector SIFT operator for interest point detection in hyperspectral imagery","authors":"Leidy P. Dorado-Muñoz, M. Velez-Reyes, A. Mukherjee, B. Roysam","doi":"10.1109/WHISPERS.2010.5594965","DOIUrl":"https://doi.org/10.1109/WHISPERS.2010.5594965","url":null,"abstract":"An algorithm for automated extraction of interest points (IP) in hyperspectral images is presented. IP are features of the image that capture information from its neighbors and are distinctive and stable under translation and rotation. IP operators for gray level images were proposed more than a decade ago and have since been studied extensively. IP are helpful in data reduction to reduce the computational burden of various algorithms by replacing an exhaustive search over the entire image domain by a probe into a concise set of highly informative points. The vector SIFT approach extends Lowe's IP operator that uses local extrema of Difference of Gaussian at multiple scales to detect interest point in gray level images by direct conversion of scalar operations such as scale-space generation, and extreme point detection into operations that take the vector nature of the image into consideration. Vector anisotropic diffusion is used for scale-space generation which enhances edges and improves IP detection. Experiments with hyperspectral images of different spatial resolutions and evaluation of IP found based on image registration is presented.","PeriodicalId":193944,"journal":{"name":"2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127986077","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}

引用次数: 6

Monitoring inland waters with the APEX sensor, a wavelet approach 用APEX传感器监测内陆水域，这是一种小波方法

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/whispers.2010.5594860

E. Knaeps, D. Raymaekers, S. Sterckx, L. Bertels, D. Odermatt

引用次数: 1

Current ground-based LWIR his remote sensing activities at Defense R&D Canada — Valcartier 目前地面LWIR遥感活动在加拿大国防研发中心进行

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594913

J. Thériault, E. Puckrin, H. Lavoie, François Bouffard, C. Turcotte, J. Lévesque

{"title":"Current ground-based LWIR his remote sensing activities at Defense R&D Canada — Valcartier","authors":"J. Thériault, E. Puckrin, H. Lavoie, François Bouffard, C. Turcotte, J. Lévesque","doi":"10.1109/WHISPERS.2010.5594913","DOIUrl":"https://doi.org/10.1109/WHISPERS.2010.5594913","url":null,"abstract":"Recently, DRDC Valcartier has been investigating novel ground-based longwave hyperspectral imaging (HSI) remote sensing techniques. Specific projects include the development of a new ground-based sensor called MoDDIFS (Multi-Option Differential Detection and Imaging Fourier Spectrometer), which is a leading edge infrared (IR) hyperspectral imaging (HSI) sensor optimized for the standoff detection of explosive vapours and precursors. The development of the MoDDIFS sensor is based on the integration of two innovative technologies: (1) the differential Fourier-transform infrared (FTIR) radiometry technology found in the Compact Atmospheric Sounding Interferometer (CATSI) previously developed by DRDC Valcartier, and (2) the HSI technology developed by Telops. The MoDDIFS sensor will offer the optical subtraction capability of the CATSI system but at high-spatial resolution using an MCT focal plane array of 84×84 pixels. The MoDDIFS sensor offers the potential of simultaneously measuring differential linear polarizations to further reduce the clutter in the measured radiance.","PeriodicalId":193944,"journal":{"name":"2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129772066","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}

引用次数: 0

Retrieving Mars aerosol optical depth from CRISM/MRO imagery 从CRISM/MRO图像中反演火星气溶胶光学深度

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594928

S. Douté, X. Ceamanos

引用次数: 10

Lossless compression of hyperspectral data obtained from Fourier-transform infrared imaging spectrometers 从傅里叶变换红外成像光谱仪获得的高光谱数据无损压缩

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594883

Julien Roy, S. Potvin, J. Deschênes, J. Genest

引用次数: 0

Non-negative matrix factorization pansharpening of hyperspectral data: An application to mid-infrared astronomy 高光谱数据的非负矩阵分解泛锐化:在中红外天文学中的应用

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594900

O. Berné, A. Helens, P. Pilleri, C. Joblin

引用次数: 50

Locally consistent graph regularization based active learning for hyperspectral image classification 基于局部一致图正则化的主动学习高光谱图像分类

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594891

Wei Di, M. Crawford

{"title":"Locally consistent graph regularization based active learning for hyperspectral image classification","authors":"Wei Di, M. Crawford","doi":"10.1109/WHISPERS.2010.5594891","DOIUrl":"https://doi.org/10.1109/WHISPERS.2010.5594891","url":null,"abstract":"A local proximity based data regularization framework for active learning is proposed as a means to optimally construct the training set for supervised classification of hyperspectral data, thereby reducing the effort required to acquire ground reference data. Based on the \"Consistency Assumption\", a local k-nearest neighborhood Laplacian Graph based regularizer is constructed to explore local inconsistency that often results from insufficient description of the current learner for the data space. Two graph regularization methods, which differ in the approach used to construct the graph weights, are investigated. One utilizes only spectral information, while the other further incorporates local spatial information through a composite Gaussian heat kernel. The regularizer queries samples with greatest violation of the smoothness assumption based on the current model, then adjusts the decision function towards the direction that is most consistent with both labeled and unlabeled data. Experiments show excellent performance on both unlabeled and unseen data for 10 class hyperspectral image data acquired by AVIRIS, as compared to random sampling and the state-of-the-art SVMSIMPLE.","PeriodicalId":193944,"journal":{"name":"2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130984521","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}

引用次数: 12

Stochastic feature selection with distributed feature spacing for hyperspectral data 高光谱数据分布特征间隔的随机特征选择

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594951

J. Clark, M. Mendenhall, Gilbert L. Peterson

{"title":"Stochastic feature selection with distributed feature spacing for hyperspectral data","authors":"J. Clark, M. Mendenhall, Gilbert L. Peterson","doi":"10.1109/WHISPERS.2010.5594951","DOIUrl":"https://doi.org/10.1109/WHISPERS.2010.5594951","url":null,"abstract":"Feature subset selection is a well studied problem in machine learning. One short-coming of many methods is the selection of highly correlated features; a characteristic of hyperspec-tral data. A novel stochastic feature selection method with three major components is presented. First, we present an optimized feature selection method that maximizes a heuristic using a simulated annealing search which increases the chance of avoiding locally optimum solutions. Second, we exploit local cross correlation pair-wise amongst classes of interest to select suitable features for class discrimination. Third, we adopt the concept of distributed spacing from the multi-objective optimization community to distribute features across the spectrum in order to select less correlated features. The classification performance of our semi-embedded feature selection and classification method is demonstrated on a 12-class textile hyperspectral classification problem under several noise realizations. These results are compared with a variety of feature selection methods that cover a broad range of approaches.","PeriodicalId":193944,"journal":{"name":"2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128358089","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}

引用次数: 4

Mapping P-T conditions in hydrothermal systems using hyperspectral remote sensing and object based techniques 利用高光谱遥感和基于物体的技术测绘热液系统的P-T条件

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594896

F. Meer, F. V. Ruitenbeek, H. Werff, C. Hecker

{"title":"Mapping P-T conditions in hydrothermal systems using hyperspectral remote sensing and object based techniques","authors":"F. Meer, F. V. Ruitenbeek, H. Werff, C. Hecker","doi":"10.1109/WHISPERS.2010.5594896","DOIUrl":"https://doi.org/10.1109/WHISPERS.2010.5594896","url":null,"abstract":"Hydrothermal alteration occurs in active volcanic systems where circulating seawater results in mineral and chemical changes in the volcanic host rocks depending on pressure-temperature conditions and initial chemical composition of the host rock. As by-products of such alteration various precious metals (gold, silver, copper etc) form. Spectral matching techniques are traditionally used in geologic studies using hyperspectral data to generate surface mineral maps which allow to characterize hydrothermal alteration. Using a combination of Al-MgOh and FeOH absorption features we can link spectral features to mineral chemistry thus linking spectroscopy to geochemistry of alteration systems. With contextual image analysis techniques applied to ratio images of combined absorption features we can detect boundaries between alteration zones from hyperspectral data. This allows to reconstruct paleo fluid pathways and interpret these in terms of discharge and recharge areas which are important areas for mineral prospectivity of these systems. The facies successions are important indicators for the genetic nature of these systems. Studying the Australian hydrothermal system of the Pilbara as a proxy to mineral zonations found on the planet Mars allows us to understand the nature of these mineral distributions on Mars.","PeriodicalId":193944,"journal":{"name":"2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114727458","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}

引用次数: 1

Spatially-smooth piece-wise convex endmember detection 空间光滑的逐块凸端元检测

2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing Pub Date : 2010-06-14 DOI: 10.1109/WHISPERS.2010.5594897

Alina Zare, Ouiem Bchir, H. Frigui, P. Gader

引用次数: 17