Pub Date : 2018-09-01DOI: 10.1109/WHISPERS.2018.8747112
W. Ouerghemmi, S. Gadal, G. Mozgeris, D. Jonikavicius
Fast urbanization requires complex management of green spaces inside districts and all around the cities. In this context, the use of high-resolution imagery could give a fast overview of species distribution in the considered study zone, and could even permit species recognition by taking advantage of high spectral resolution (i.e. superspectral/hyperspectral imagery). In this study, we aim to explore the feasibility of eight vegetation species recognition inside Kaunas city (Lithuania). The goal is to determine the potential of metric/centimetric spatial resolution imagery with less than hundred bands and a limited spectral interval (e.g. Vis-NIR), to be able to recognize urban vegetation species. The ground truth samples were also limited for some of the considered species. The method included pre-treatments based on vegetation masking and feature selection using Minimum Noise Fraction (MNF). Support Vector Machine (based classifier) showed encouraging performance over Spectral Angle Mapper (SAM), the accuracies were not notably high in term of statistical analysis (i.e. up to 46% of overall accuracy) but the visual inspection showed coherent distribution of the detected species.
{"title":"Urban vegetation mapping by airborne hyperspetral imagery; feasibility and limitations","authors":"W. Ouerghemmi, S. Gadal, G. Mozgeris, D. Jonikavicius","doi":"10.1109/WHISPERS.2018.8747112","DOIUrl":"https://doi.org/10.1109/WHISPERS.2018.8747112","url":null,"abstract":"Fast urbanization requires complex management of green spaces inside districts and all around the cities. In this context, the use of high-resolution imagery could give a fast overview of species distribution in the considered study zone, and could even permit species recognition by taking advantage of high spectral resolution (i.e. superspectral/hyperspectral imagery). In this study, we aim to explore the feasibility of eight vegetation species recognition inside Kaunas city (Lithuania). The goal is to determine the potential of metric/centimetric spatial resolution imagery with less than hundred bands and a limited spectral interval (e.g. Vis-NIR), to be able to recognize urban vegetation species. The ground truth samples were also limited for some of the considered species. The method included pre-treatments based on vegetation masking and feature selection using Minimum Noise Fraction (MNF). Support Vector Machine (based classifier) showed encouraging performance over Spectral Angle Mapper (SAM), the accuracies were not notably high in term of statistical analysis (i.e. up to 46% of overall accuracy) but the visual inspection showed coherent distribution of the detected species.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124643943","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.2016.8071801
S. Prasad, T. Priya, M. Cui, Shishir K. Shah
Person re-identification in a multi-camera environment is an important part of modern surveillance systems. Person re-identification from color images has been the focus of much active research, due to the numerous challenges posed with such analysis tasks, such as variations in illumination, pose and viewpoints. In this paper, we suggest that hyperspectral imagery has the potential to provide unique information that is expected to be beneficial for the re-identification task. Specifically, we assert that by accurately characterizing the unique spectral signature for each person's skin, hyperspectral imagery can provide very useful descriptors (e.g. spectral signatures from skin pixels) for re-identification. Towards this end, we acquired proof-of-concept hyperspectral reidentification data under challenging (practical) conditions from 15 people. Our results indicate that hyperspectral data result in a substantially enhanced re-identification performance compared to color (RGB) images, when using spectral signatures over skin as the feature descriptor.
{"title":"Person re-identification with hyperspectral multi-camera systems #x2014; A pilot study","authors":"S. Prasad, T. Priya, M. Cui, Shishir K. Shah","doi":"10.1109/WHISPERS.2016.8071801","DOIUrl":"https://doi.org/10.1109/WHISPERS.2016.8071801","url":null,"abstract":"Person re-identification in a multi-camera environment is an important part of modern surveillance systems. Person re-identification from color images has been the focus of much active research, due to the numerous challenges posed with such analysis tasks, such as variations in illumination, pose and viewpoints. In this paper, we suggest that hyperspectral imagery has the potential to provide unique information that is expected to be beneficial for the re-identification task. Specifically, we assert that by accurately characterizing the unique spectral signature for each person's skin, hyperspectral imagery can provide very useful descriptors (e.g. spectral signatures from skin pixels) for re-identification. Towards this end, we acquired proof-of-concept hyperspectral reidentification data under challenging (practical) conditions from 15 people. Our results indicate that hyperspectral data result in a substantially enhanced re-identification performance compared to color (RGB) images, when using spectral signatures over skin as the feature descriptor.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","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":"129674942","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 : 2012-06-04DOI: 10.1109/WHISPERS.2012.6874291
Shunshi Hu, Lifu Zhang
Extraterrestrial Solar Spectral Irradiance (ESSI) is an important parameter for calculating Mean Solar Exoatmospheric Irradiance (MSEI) of each band for a given satellite. In order to find optimal ESSI dataset for calculation of MSEI, 5 ESSI datasets from MODTRAN4.0 software and ESSI dataset simulated by Santa Barbara DISORT Atmospheric Radiative Transfer (SBDART) tool were selected to compute MSEI of each band for HJ-1A CCD1, CEBERS02 CCD, Landsat TM5(band1~band4) and ASTER(band1~band9). Comparisons between the calculated MSEI and the published MSEI were made. It is found that ESSI dataset simulated by SBDART tool and MODTRAN oldkur.dat dataset are best suitable for calculation of MSEI and the MSEI results are consistent with published MSEI. There are big errors using thkur.dat and newkur.dat datasets to compute MSEI for these satellites, so that they are not recommended to calculate MSEI for given satellites.
地外太阳光谱辐照度(ESSI)是计算给定卫星各波段平均太阳大气外辐照度(MSEI)的重要参数。选取MODTRAN4.0软件中的5个ESSI数据集和Santa Barbara DISORT Atmospheric radiation Transfer (SBDART)工具模拟的ESSI数据集，计算HJ-1A CCD1、CEBERS02 CCD、Landsat TM5(band1~band4)和ASTER(band1~band9)各波段的MSEI。将计算的MSEI与公布的MSEI进行了比较。结果表明，SBDART工具模拟的ESSI数据集和MODTRAN oldkur.dat数据集最适合MSEI的计算，MSEI结果与已发表的MSEI结果一致。使用thkur.dat和newkur.dat数据集计算这些卫星的MSEI存在较大的误差，因此不建议对给定卫星计算MSEI。
{"title":"Selection of different Extraterrestrial Solar Spectral Irradiance datasets and its effects on Mean Solar Exoatmospheric Irradiance","authors":"Shunshi Hu, Lifu Zhang","doi":"10.1109/WHISPERS.2012.6874291","DOIUrl":"https://doi.org/10.1109/WHISPERS.2012.6874291","url":null,"abstract":"Extraterrestrial Solar Spectral Irradiance (ESSI) is an important parameter for calculating Mean Solar Exoatmospheric Irradiance (MSEI) of each band for a given satellite. In order to find optimal ESSI dataset for calculation of MSEI, 5 ESSI datasets from MODTRAN4.0 software and ESSI dataset simulated by Santa Barbara DISORT Atmospheric Radiative Transfer (SBDART) tool were selected to compute MSEI of each band for HJ-1A CCD1, CEBERS02 CCD, Landsat TM5(band1~band4) and ASTER(band1~band9). Comparisons between the calculated MSEI and the published MSEI were made. It is found that ESSI dataset simulated by SBDART tool and MODTRAN oldkur.dat dataset are best suitable for calculation of MSEI and the MSEI results are consistent with published MSEI. There are big errors using thkur.dat and newkur.dat datasets to compute MSEI for these satellites, so that they are not recommended to calculate MSEI for given satellites.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130259697","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 : 2012-06-04DOI: 10.1109/WHISPERS.2012.6874239
Jianding Ding, T. Tiyip, Yuan Yao, Zhenliang Zhao, Fei Zhang
This study selected the Weigan- Kuqa river delta oasis in Xinjiang, where located a large areas of saline soil as the study area, using EM38 conductivity meter and ASD Field Spec Pro FR spectrometer, studied the correlation relationship between the arid zone saline soil hyper spectral and surface soil conductivity. The soil conductivity estimating model under the 3 different spectral index is established. And the scientific basis for saline soil remote sensing monitoring in a further way was provided.
本研究选取新疆渭干—库车河三角洲绿洲大面积盐渍土为研究区，采用EM38电导率仪和ASD Field Spec Pro FR光谱仪，研究干旱区盐渍土高光谱与表层土壤电导率的相关关系。建立了3种不同光谱指数下的土壤电导率估算模型。为进一步开展盐渍土遥感监测提供了科学依据。
{"title":"The study of correlation analysis between the saline soil hyperspectral reflectance and the surface soil conductivity at the Weigan-Kuqa rivers delta oasis","authors":"Jianding Ding, T. Tiyip, Yuan Yao, Zhenliang Zhao, Fei Zhang","doi":"10.1109/WHISPERS.2012.6874239","DOIUrl":"https://doi.org/10.1109/WHISPERS.2012.6874239","url":null,"abstract":"This study selected the Weigan- Kuqa river delta oasis in Xinjiang, where located a large areas of saline soil as the study area, using EM38 conductivity meter and ASD Field Spec Pro FR spectrometer, studied the correlation relationship between the arid zone saline soil hyper spectral and surface soil conductivity. The soil conductivity estimating model under the 3 different spectral index is established. And the scientific basis for saline soil remote sensing monitoring in a further way was provided.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115799415","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 : 1900-01-01DOI: 10.1109/WHISPERS.2014.8077618
Guorui Jia, Huijie Zhao, Dongxing Tao, Kewang Deng
To promote cross-calibration or information extraction involving hyperspectral reflectance data from different sources, a method for restoring reflectance of a higher spectral resolution from hyperspectral radiance data is proposed. It involves three steps: spectral super-resolution of radiance data, transformation to the higher resolution of interest, and radiative-transfer-model-based atmospheric correction. The spectral resolution of the super-resolved radiance and the spectral response model of the restored reflectance were analyzed. The restored reflectance matches the library spectrum better than the directly inversed and the interpolated reflectance spectra in the validation experiment based on HyMap data and USGS spectral library. This method is theoretically applicable to get reflectance of a relative lower spectral resolution as well.
{"title":"Inversing reflectance of higher resolution from hyperspectral radiance data based on spectral super-resolution","authors":"Guorui Jia, Huijie Zhao, Dongxing Tao, Kewang Deng","doi":"10.1109/WHISPERS.2014.8077618","DOIUrl":"https://doi.org/10.1109/WHISPERS.2014.8077618","url":null,"abstract":"To promote cross-calibration or information extraction involving hyperspectral reflectance data from different sources, a method for restoring reflectance of a higher spectral resolution from hyperspectral radiance data is proposed. It involves three steps: spectral super-resolution of radiance data, transformation to the higher resolution of interest, and radiative-transfer-model-based atmospheric correction. The spectral resolution of the super-resolved radiance and the spectral response model of the restored reflectance were analyzed. The restored reflectance matches the library spectrum better than the directly inversed and the interpolated reflectance spectra in the validation experiment based on HyMap data and USGS spectral library. This method is theoretically applicable to get reflectance of a relative lower spectral resolution as well.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"47 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129997679","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}
Leaf area index (LAI) is an important parameter which always be used to estimate vegetation cover and forecast the crop growth and yield. Currently the statistic relationship between LAI and vegetation indices (VI) has been widely applied to predict vegetation LAI. Each vegetation index for inversing LAI has applicable area and conditions, the best vegetation index or spectral parameter of them were not sure for estimating LAI of winter wheat in China. In this paper, PSR-3500 spectrometer and LAI-2200 plant canopy analyser were used to acquire the spectrum and LAI synchronously from April to June in 2013, in xiaotangshan of Beijing. After calculating VIs selected in this study, the correlation relationships between VIs and LAI were established under different spectral widths and center wavelengths. The results show that DVI is the best index with R2 of 0.7. 3nm was verified the best bandwidth with center wavelength of NIR and red was 815nm and 746nm, respectively. The method that multiple VIs were used to inverse LAI synergistically, was proposed in this paper, which established the optimal linear regression model. Finally, the R2 we got between prediction LAI and the measured value reached to 0.9235, which reaffirmed the feasibility of multiple VIs in the estimation of vegetation LAI.
{"title":"Evaluating different vegetation index for estimating lai of winter wheat using hyperspectral remote sensing data","authors":"Jingguo Tian, Shudong Wang, Lifu Zhang, Taixia Wu, X. She, Hailing Jiang","doi":"10.1109/WHISPERS.2015.8075437","DOIUrl":"https://doi.org/10.1109/WHISPERS.2015.8075437","url":null,"abstract":"Leaf area index (LAI) is an important parameter which always be used to estimate vegetation cover and forecast the crop growth and yield. Currently the statistic relationship between LAI and vegetation indices (VI) has been widely applied to predict vegetation LAI. Each vegetation index for inversing LAI has applicable area and conditions, the best vegetation index or spectral parameter of them were not sure for estimating LAI of winter wheat in China. In this paper, PSR-3500 spectrometer and LAI-2200 plant canopy analyser were used to acquire the spectrum and LAI synchronously from April to June in 2013, in xiaotangshan of Beijing. After calculating VIs selected in this study, the correlation relationships between VIs and LAI were established under different spectral widths and center wavelengths. The results show that DVI is the best index with R2 of 0.7. 3nm was verified the best bandwidth with center wavelength of NIR and red was 815nm and 746nm, respectively. The method that multiple VIs were used to inverse LAI synergistically, was proposed in this paper, which established the optimal linear regression model. Finally, the R2 we got between prediction LAI and the measured value reached to 0.9235, which reaffirmed the feasibility of multiple VIs in the estimation of vegetation LAI.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116504461","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 : 1900-01-01DOI: 10.1109/WHISPERS52202.2021.9483991
G. Sicot, M. Ghannami, M. Lennon, S. Loyer
Hyperspectral sensors provide informative data in many fields related to Earth observation. On the coastal zone, the inversion of radiative transfer models of the light has shown the ability to estimate parameters characterizing the water column. Particularly the water column depth, its concentration of non-algal particles, in phytoplankton, and the bottom reflectance can be retrieved. In this paper, the ability of hyper-spectral data to estimate the parameters of the coastal zone thanks to the semi-analytical Lee model is studied according to the way the measurement is made: number of bands, impact of spectral response at each band and without any additional concepts such as probabilistic concepts.
{"title":"Estimability Study of the Parameters of the Semi-Analytical Lee Model with Hyperspectral Data","authors":"G. Sicot, M. Ghannami, M. Lennon, S. Loyer","doi":"10.1109/WHISPERS52202.2021.9483991","DOIUrl":"https://doi.org/10.1109/WHISPERS52202.2021.9483991","url":null,"abstract":"Hyperspectral sensors provide informative data in many fields related to Earth observation. On the coastal zone, the inversion of radiative transfer models of the light has shown the ability to estimate parameters characterizing the water column. Particularly the water column depth, its concentration of non-algal particles, in phytoplankton, and the bottom reflectance can be retrieved. In this paper, the ability of hyper-spectral data to estimate the parameters of the coastal zone thanks to the semi-analytical Lee model is studied according to the way the measurement is made: number of bands, impact of spectral response at each band and without any additional concepts such as probabilistic concepts.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"11 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133506398","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 : 1900-01-01DOI: 10.1109/WHISPERS.2012.6874241
Ping Zhou, Xiao Guan, Huarui Wang
The spectralogy of soil remote sensing is a product of soil science and remote sensing spectroscopy, and it studies soil properties by revealing the soil spectral characteristics. This paper describes the basic theory and methods of the spectralogy of soil remote sensing and gives a preliminary discussion on the soil spectrum uncertainty. Finally, a summary is given to its application in the evaluation of soil properties, soil classification and mapping.
{"title":"The theory and application of the spectralogy of soil Remote Sensing","authors":"Ping Zhou, Xiao Guan, Huarui Wang","doi":"10.1109/WHISPERS.2012.6874241","DOIUrl":"https://doi.org/10.1109/WHISPERS.2012.6874241","url":null,"abstract":"The spectralogy of soil remote sensing is a product of soil science and remote sensing spectroscopy, and it studies soil properties by revealing the soil spectral characteristics. This paper describes the basic theory and methods of the spectralogy of soil remote sensing and gives a preliminary discussion on the soil spectrum uncertainty. Finally, a summary is given to its application in the evaluation of soil properties, soil classification and mapping.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114599173","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 : 1900-01-01DOI: 10.1109/WHISPERS.2019.8920979
Chunyang Zhu, Jianhua Wang, Shanwei Liu, H. Sheng, Yanfang Xiao
Sea fog can have both negative and positive impacts on humans life. At present, remote sensing has become the main means of long-term and large-scale observation of sea fog. With the improvement of spectral resolution and increase of data volume, the traditional threshold method is simple and convenient as the main method of current sea fog detection, but it’s not flexible and accurate enough which causes people need a more automated and intelligent algorithm to achieve efficient sea fog detection. In this article, we use the U-Net deep learning model to construct the sea fog detection model for MODIS multi-spectral images. The main steps include? (1) Data preprocessing, including the PCA method for dimensionality reduction of data; (2) Manual samples extraction with CALIPSO data assist; (3) Construction and training of U-Net sea fog detection model. The experimental results show that the U-Net model can effectively and machine learning method has good potential in sea fog detection.
{"title":"Sea Fog Detection Using U-Net Deep Learning Model Based On Modis Data","authors":"Chunyang Zhu, Jianhua Wang, Shanwei Liu, H. Sheng, Yanfang Xiao","doi":"10.1109/WHISPERS.2019.8920979","DOIUrl":"https://doi.org/10.1109/WHISPERS.2019.8920979","url":null,"abstract":"Sea fog can have both negative and positive impacts on humans life. At present, remote sensing has become the main means of long-term and large-scale observation of sea fog. With the improvement of spectral resolution and increase of data volume, the traditional threshold method is simple and convenient as the main method of current sea fog detection, but it’s not flexible and accurate enough which causes people need a more automated and intelligent algorithm to achieve efficient sea fog detection. In this article, we use the U-Net deep learning model to construct the sea fog detection model for MODIS multi-spectral images. The main steps include? (1) Data preprocessing, including the PCA method for dimensionality reduction of data; (2) Manual samples extraction with CALIPSO data assist; (3) Construction and training of U-Net sea fog detection model. The experimental results show that the U-Net model can effectively and machine learning method has good potential in sea fog detection.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128870056","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 : 1900-01-01DOI: 10.1109/WHISPERS.2010.5594892
Peijun Du, J. Xia, W. Cao, Xiaoling Wang
Taking Xuzhou city as the case study area, EO-1 Hyperion hyperspectral remote sensing image captured in 2004 was chosen as the data source to extract impervious surface area (ISA) by spectral mixture analysis using LSMM model. In order to demonstrate the advantages of hyperspectral images and LSMM for ISA extraction, hyperspectral image was compared with multispectral Landsat TM image, and LSMM was compared with traditional hard classifiers, indicating that hyperspectral image is more effective than multispectral data for urban impervious surface extraction, and unmixing is superior to hard classification methods.
{"title":"Extraction of urban impervious surface from hyperspectral remote sensing image","authors":"Peijun Du, J. Xia, W. Cao, Xiaoling Wang","doi":"10.1109/WHISPERS.2010.5594892","DOIUrl":"https://doi.org/10.1109/WHISPERS.2010.5594892","url":null,"abstract":"Taking Xuzhou city as the case study area, EO-1 Hyperion hyperspectral remote sensing image captured in 2004 was chosen as the data source to extract impervious surface area (ISA) by spectral mixture analysis using LSMM model. In order to demonstrate the advantages of hyperspectral images and LSMM for ISA extraction, hyperspectral image was compared with multispectral Landsat TM image, and LSMM was compared with traditional hard classifiers, indicating that hyperspectral image is more effective than multispectral data for urban impervious surface extraction, and unmixing is superior to hard classification methods.","PeriodicalId":377495,"journal":{"name":"Workshop on Hyperspectral Image and Signal Processing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114746616","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：