面向高光谱影像分类的显著性特征提取方法

针对高光谱影像分类问题，提出了一种显著性特征提取方法。首先，利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后，基于分割得到的小区域计算反映不同区域的显著性特征。最后，沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合，并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明，与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比，提取的显著性特征能够获得更高的高光谱影像分类精度，且结合光谱特征能够进一步提高分类精...

Full description

Saved in:
Bibliographic Details
Published in:Ce hui xue bao 2019-08, Vol.48 (8), p.985
Main Authors: 余岸竹, 刘冰, 邢志鹏, 杨帆, 杨其淼
Format: Article
Language:chi ; eng
Subjects:
Algorithms
Artificial neural networks
Classification
Feature extraction
Hyperspectral imaging
Image classification
Image segmentation
Neural networks
Support vector machines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue 8
container_start_page 985
container_title Ce hui xue bao
container_volume 48
creator 余岸竹
刘冰
邢志鹏
杨帆
杨其淼
description 针对高光谱影像分类问题，提出了一种显著性特征提取方法。首先，利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后，基于分割得到的小区域计算反映不同区域的显著性特征。最后，沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合，并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明，与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比，提取的显著性特征能够获得更高的高光谱影像分类精度，且结合光谱特征能够进一步提高分类精度。
doi_str_mv 10.11947/j.AGCS.2019.20180499
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2583481091</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2583481091</sourcerecordid><originalsourceid>FETCH-proquest_journals_25834810913</originalsourceid><addsrcrecordid>eNpjYJA1NNAzNLQ0MdfP0nN0dw7WMzIwtAQRFgYmlpZMDJyGBgaGuoamlqYsSGwOBq7i4iwDA1MLEzNTTgbLl3MXPZ0w8eXqGU9bO19s2Ph078anzf1PO9qeb9z9fFbLsxn7Xkyc_qxh-fPOnU_3NT7rn_C0f9qzaTufbZ7Kw8CalphTnMoLpbkZlN1cQ5w9dAuK8gtLU4tL4rPyS4vygFLxRqYWxiYWhgaWhsbEqQIAbc1Q6w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2583481091</pqid></control><display><type>article</type><title>面向高光谱影像分类的显著性特征提取方法</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>余岸竹 ; 刘冰 ; 邢志鹏 ; 杨帆 ; 杨其淼</creator><creatorcontrib>余岸竹 ; 刘冰 ; 邢志鹏 ; 杨帆 ; 杨其淼</creatorcontrib><description>针对高光谱影像分类问题，提出了一种显著性特征提取方法。首先，利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后，基于分割得到的小区域计算反映不同区域的显著性特征。最后，沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合，并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明，与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比，提取的显著性特征能够获得更高的高光谱影像分类精度，且结合光谱特征能够进一步提高分类精度。</description><identifier>ISSN: 1001-1595</identifier><identifier>EISSN: 1001-1595</identifier><identifier>DOI: 10.11947/j.AGCS.2019.20180499</identifier><language>chi ; eng</language><publisher>Beijing: Surveying and Mapping Press</publisher><subject>Algorithms ; Artificial neural networks ; Classification ; Feature extraction ; Hyperspectral imaging ; Image classification ; Image segmentation ; Neural networks ; Support vector machines</subject><ispartof>Ce hui xue bao, 2019-08, Vol.48 (8), p.985</ispartof><rights>Aug 2019. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2583481091?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,25753,27924,27925,37012,44590</link.rule.ids></links><search><creatorcontrib>余岸竹</creatorcontrib><creatorcontrib>刘冰</creatorcontrib><creatorcontrib>邢志鹏</creatorcontrib><creatorcontrib>杨帆</creatorcontrib><creatorcontrib>杨其淼</creatorcontrib><title>面向高光谱影像分类的显著性特征提取方法</title><title>Ce hui xue bao</title><description>针对高光谱影像分类问题，提出了一种显著性特征提取方法。首先，利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后，基于分割得到的小区域计算反映不同区域的显著性特征。最后，沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合，并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明，与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比，提取的显著性特征能够获得更高的高光谱影像分类精度，且结合光谱特征能够进一步提高分类精度。</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Classification</subject><subject>Feature extraction</subject><subject>Hyperspectral imaging</subject><subject>Image classification</subject><subject>Image segmentation</subject><subject>Neural networks</subject><subject>Support vector machines</subject><issn>1001-1595</issn><issn>1001-1595</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYJA1NNAzNLQ0MdfP0nN0dw7WMzIwtAQRFgYmlpZMDJyGBgaGuoamlqYsSGwOBq7i4iwDA1MLEzNTTgbLl3MXPZ0w8eXqGU9bO19s2Ph078anzf1PO9qeb9z9fFbLsxn7Xkyc_qxh-fPOnU_3NT7rn_C0f9qzaTufbZ7Kw8CalphTnMoLpbkZlN1cQ5w9dAuK8gtLU4tL4rPyS4vygFLxRqYWxiYWhgaWhsbEqQIAbc1Q6w</recordid><startdate>20190801</startdate><enddate>20190801</enddate><creator>余岸竹</creator><creator>刘冰</creator><creator>邢志鹏</creator><creator>杨帆</creator><creator>杨其淼</creator><general>Surveying and Mapping Press</general><scope>3V.</scope><scope>7X2</scope><scope>8FE</scope><scope>8FH</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>BKSAR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>LK8</scope><scope>M0K</scope><scope>M7P</scope><scope>PATMY</scope><scope>PCBAR</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PYCSY</scope></search><sort><creationdate>20190801</creationdate><title>面向高光谱影像分类的显著性特征提取方法</title><author>余岸竹 ; 刘冰 ; 邢志鹏 ; 杨帆 ; 杨其淼</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25834810913</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>chi ; eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Classification</topic><topic>Feature extraction</topic><topic>Hyperspectral imaging</topic><topic>Image classification</topic><topic>Image segmentation</topic><topic>Neural networks</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>余岸竹</creatorcontrib><creatorcontrib>刘冰</creatorcontrib><creatorcontrib>邢志鹏</creatorcontrib><creatorcontrib>杨帆</creatorcontrib><creatorcontrib>杨其淼</creatorcontrib><collection>ProQuest Central (Corporate)</collection><collection>Agricultural Science Collection</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest Natural Science Collection</collection><collection>Earth, Atmospheric &amp; Aquatic Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Biological Science Collection</collection><collection>Agriculture Science Database</collection><collection>Biological Science Database</collection><collection>Environmental Science Database</collection><collection>Earth, Atmospheric &amp; Aquatic Science Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Environmental Science Collection</collection><jtitle>Ce hui xue bao</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>余岸竹</au><au>刘冰</au><au>邢志鹏</au><au>杨帆</au><au>杨其淼</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>面向高光谱影像分类的显著性特征提取方法</atitle><jtitle>Ce hui xue bao</jtitle><date>2019-08-01</date><risdate>2019</risdate><volume>48</volume><issue>8</issue><spage>985</spage><pages>985-</pages><issn>1001-1595</issn><eissn>1001-1595</eissn><abstract>针对高光谱影像分类问题，提出了一种显著性特征提取方法。首先，利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后，基于分割得到的小区域计算反映不同区域的显著性特征。最后，沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合，并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明，与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比，提取的显著性特征能够获得更高的高光谱影像分类精度，且结合光谱特征能够进一步提高分类精度。</abstract><cop>Beijing</cop><pub>Surveying and Mapping Press</pub><doi>10.11947/j.AGCS.2019.20180499</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1001-1595
ispartof Ce hui xue bao, 2019-08, Vol.48 (8), p.985
issn 1001-1595
1001-1595
language chi ; eng
recordid cdi_proquest_journals_2583481091
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Algorithms
Artificial neural networks
Classification
Feature extraction
Hyperspectral imaging
Image classification
Image segmentation
Neural networks
Support vector machines
title 面向高光谱影像分类的显著性特征提取方法
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T15%3A43%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=%E9%9D%A2%E5%90%91%E9%AB%98%E5%85%89%E8%B0%B1%E5%BD%B1%E5%83%8F%E5%88%86%E7%B1%BB%E7%9A%84%E6%98%BE%E8%91%97%E6%80%A7%E7%89%B9%E5%BE%81%E6%8F%90%E5%8F%96%E6%96%B9%E6%B3%95&rft.jtitle=Ce%20hui%20xue%20bao&rft.au=%E4%BD%99%E5%B2%B8%E7%AB%B9&rft.date=2019-08-01&rft.volume=48&rft.issue=8&rft.spage=985&rft.pages=985-&rft.issn=1001-1595&rft.eissn=1001-1595&rft_id=info:doi/10.11947/j.AGCS.2019.20180499&rft_dat=%3Cproquest%3E2583481091%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_25834810913%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2583481091&rft_id=info:pmid/&rfr_iscdi=true