面向土地覆盖精准分类的遥感特征参数优选方法
P237; 在显著气候变化叠加人类活动干扰的背景下,可持续的自然资源管理对于精准掌握土地覆盖信息的需求不断提升.为应对地表形态的复杂性、地物类型的多样性、遥感图像特征的非线性给传统遥感图像分类方法带来的挑战,本文基于随机森林Gini指数,提出了一种10％阈值决策的遥感特征参数优选方法,旨在筛选出最优的遥感特征参数组合,达到最佳土地覆盖分类效果.首先,选择光谱特征、纹理特征、温热特征、高程特征、主成分特征组成遥感影像堆栈.然后,设置多组决策树对特征贡献度进行交叉验证,并根据特征重要性的归一化均值确定特征排序.最后,设定阈值,筛选出符合要求的遥感特征参数,并迭代过程.选择覆盖江苏盐城自然保护区的S...
Saved in:
| Published in | 测绘学报 Vol. 53; no. 7; pp. 1401 - 1416 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
浙江海洋大学海洋科学与技术学院,浙江舟山 316022%宁波大学地理与空间信息技术系,浙江宁波 315211%浙江海洋大学海洋科学与技术学院,浙江舟山 316022%浙江省水文地质工程地质大队,浙江宁波 315012
12.08.2024
苏州科技大学地理科学与测绘工程学院,江苏苏州 215009%中国地质大学(武汉)地球物理与空间信息学院,湖北武汉 430074 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-1595 |
| DOI | 10.11947/j.AGCS.2024.20230327 |
Cover
| Abstract | P237; 在显著气候变化叠加人类活动干扰的背景下,可持续的自然资源管理对于精准掌握土地覆盖信息的需求不断提升.为应对地表形态的复杂性、地物类型的多样性、遥感图像特征的非线性给传统遥感图像分类方法带来的挑战,本文基于随机森林Gini指数,提出了一种10％阈值决策的遥感特征参数优选方法,旨在筛选出最优的遥感特征参数组合,达到最佳土地覆盖分类效果.首先,选择光谱特征、纹理特征、温热特征、高程特征、主成分特征组成遥感影像堆栈.然后,设置多组决策树对特征贡献度进行交叉验证,并根据特征重要性的归一化均值确定特征排序.最后,设定阈值,筛选出符合要求的遥感特征参数,并迭代过程.选择覆盖江苏盐城自然保护区的Sentinel-2遥感图像开展试验,结果表明,本文方法筛选出的遥感特征参数代表性好,与CART、SVM、KNN和只使用波段信息的RF相比,分类结果地物边界清晰,类别属性准确,总体精度和Kappa系数分别为96.20％和0.955 6.本文研究能够为区域空间规划和可持续发展提供技术支持. |
|---|---|
| AbstractList | P237; 在显著气候变化叠加人类活动干扰的背景下,可持续的自然资源管理对于精准掌握土地覆盖信息的需求不断提升.为应对地表形态的复杂性、地物类型的多样性、遥感图像特征的非线性给传统遥感图像分类方法带来的挑战,本文基于随机森林Gini指数,提出了一种10％阈值决策的遥感特征参数优选方法,旨在筛选出最优的遥感特征参数组合,达到最佳土地覆盖分类效果.首先,选择光谱特征、纹理特征、温热特征、高程特征、主成分特征组成遥感影像堆栈.然后,设置多组决策树对特征贡献度进行交叉验证,并根据特征重要性的归一化均值确定特征排序.最后,设定阈值,筛选出符合要求的遥感特征参数,并迭代过程.选择覆盖江苏盐城自然保护区的Sentinel-2遥感图像开展试验,结果表明,本文方法筛选出的遥感特征参数代表性好,与CART、SVM、KNN和只使用波段信息的RF相比,分类结果地物边界清晰,类别属性准确,总体精度和Kappa系数分别为96.20％和0.955 6.本文研究能够为区域空间规划和可持续发展提供技术支持. |
| Abstract_FL | Sustainable natural resources management requires considerable accurate land cover information given the evident cli-mate change impacts and human disturbances on wetlands.It is characterized by the convergence of numerous materials and en-ergies,resulting in fragmented landscapes and frequent land cover changes.To address the challenges posed by the complexity of landforms,diversity of land cover types,and non-linearity of remote sensing image features in traditional remote sensing im-age classification methods,this paper proposes a feature parameter selection method based on the Gini index of random forests,with a 10％threshold decision.The aim is to identify the optimal combination of remote sensing feature parameters.Firstly,spectral features,texture features,thermal features,elevation features,and principal component features are selected to form a stack of remote sensing images.Then,multiple decision trees are set up to cross-validate the contributions of the features,and the feature ranking is determined based on the normalized mean importance of the features.Finally,a threshold is set to select the remote sensing feature parameters that meet the requirements,and the process is iterated.Experiments are conduc-ted using Sentinel-2 remote sensing images covering the Yancheng Nature Reserve in Jiangsu province.The results show that the remote sensing feature parameters selected by this method have good representativeness.Compared with CART,SVM,KNN,and RF methods that only use band information,the proposed method produces clearer boundaries and more accurate category attributes in the classification results,with an overall accuracy of 96.20％and a Kappa coefficient of 0.955 6.This re-search can provide technical support for regional spatial planning and sustainable development. |
| Author | 孙伟伟 梁锦涛 王建强 杨刚 龚绍军 陈超 |
| AuthorAffiliation | 苏州科技大学地理科学与测绘工程学院,江苏苏州 215009%中国地质大学(武汉)地球物理与空间信息学院,湖北武汉 430074;浙江海洋大学海洋科学与技术学院,浙江舟山 316022%宁波大学地理与空间信息技术系,浙江宁波 315211%浙江海洋大学海洋科学与技术学院,浙江舟山 316022%浙江省水文地质工程地质大队,浙江宁波 315012 |
| AuthorAffiliation_xml | – name: 苏州科技大学地理科学与测绘工程学院,江苏苏州 215009%中国地质大学(武汉)地球物理与空间信息学院,湖北武汉 430074;浙江海洋大学海洋科学与技术学院,浙江舟山 316022%宁波大学地理与空间信息技术系,浙江宁波 315211%浙江海洋大学海洋科学与技术学院,浙江舟山 316022%浙江省水文地质工程地质大队,浙江宁波 315012 |
| Author_FL | GONG Shaojun YANG Gang CHEN Chao LIANG Jintao SUN Weiwei WANG Jianqiang |
| Author_FL_xml | – sequence: 1 fullname: CHEN Chao – sequence: 2 fullname: LIANG Jintao – sequence: 3 fullname: YANG Gang – sequence: 4 fullname: SUN Weiwei – sequence: 5 fullname: GONG Shaojun – sequence: 6 fullname: WANG Jianqiang |
| Author_xml | – sequence: 1 fullname: 陈超 – sequence: 2 fullname: 梁锦涛 – sequence: 3 fullname: 杨刚 – sequence: 4 fullname: 孙伟伟 – sequence: 5 fullname: 龚绍军 – sequence: 6 fullname: 王建强 |
| BookMark | eNotjzFLw0AYhm-oYK39CY6Oqd-XL9ckk5SgVSg4qHO5i3dqkRQMoqOVEu1UHVpEKwVB56pTUfprvMT-C1t0eZ_teXiXWC5qRoqxFYQSou-4a41SpRrslmywnfkQkO3mWB4B0ELu80VWjONjCcAdcjn5ebY-fXo2t3dmMDSD0c9rkj32s_eJuU7MTZK9fWYP7WnrJW0Ps87YTFqme5X2Rt9f99PLTtofpx-9ZbagxUmsiv8ssP3Njb1gy6rtVLeDSs2KZ3GylAIIhdIkQemyz0mGgPqAc8k9Gx0uFJIou-R4ioQQWkjwJCnU6JOnOVKBrf55z0WkRXRYbzTPTqNZsR4eXcj5YXABiX4BlXNimg |
| ClassificationCodes | P237 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.11947/j.AGCS.2024.20230327 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Astronomy & Astrophysics |
| DocumentTitle_FL | Remote sensing parameters optimization for accurate land cover classifi-cation |
| EndPage | 1416 |
| ExternalDocumentID | chxb202407013 |
| GroupedDBID | -01 2B. 4A8 5VS 5XA 5XB 7X2 92E 92I 93N ABJNI ACGFS AEUYN AFKRA ALMA_UNASSIGNED_HOLDINGS ATCPS BBNVY BENPR BHPHI BKSAR CCEZO CCPQU CCVFK CW9 HCIFZ IPNFZ M0K M7P OK1 P2P PATMY PCBAR PHGZM PHGZT PIMPY PMFND PSX PYCSY RIG TCJ TGP U1G U5K |
| ID | FETCH-LOGICAL-s1003-ee00caef3b0ef6953bc01fd55b582145ae13a67348e3aaafab08b3e1f1938f513 |
| ISSN | 1001-1595 |
| IngestDate | Thu May 29 04:11:08 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 7 |
| Keywords | 特征优选 随机森林 土地覆盖分类 Gini指数 Gini index random forest feature recursive elimination land cover classification feature optimizing 递归特征消除 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1003-ee00caef3b0ef6953bc01fd55b582145ae13a67348e3aaafab08b3e1f1938f513 |
| PageCount | 16 |
| ParticipantIDs | wanfang_journals_chxb202407013 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-08-12 |
| PublicationDateYYYYMMDD | 2024-08-12 |
| PublicationDate_xml | – month: 08 year: 2024 text: 2024-08-12 day: 12 |
| PublicationDecade | 2020 |
| PublicationTitle | 测绘学报 |
| PublicationTitle_FL | Acta Geodaetica et Cartographica Sinica |
| PublicationYear | 2024 |
| Publisher | 浙江海洋大学海洋科学与技术学院,浙江舟山 316022%宁波大学地理与空间信息技术系,浙江宁波 315211%浙江海洋大学海洋科学与技术学院,浙江舟山 316022%浙江省水文地质工程地质大队,浙江宁波 315012 苏州科技大学地理科学与测绘工程学院,江苏苏州 215009%中国地质大学(武汉)地球物理与空间信息学院,湖北武汉 430074 |
| Publisher_xml | – name: 苏州科技大学地理科学与测绘工程学院,江苏苏州 215009%中国地质大学(武汉)地球物理与空间信息学院,湖北武汉 430074 – name: 浙江海洋大学海洋科学与技术学院,浙江舟山 316022%宁波大学地理与空间信息技术系,浙江宁波 315211%浙江海洋大学海洋科学与技术学院,浙江舟山 316022%浙江省水文地质工程地质大队,浙江宁波 315012 |
| SSID | ssib005437539 ssib038074662 ssib051373695 ssib002263888 ssib000862384 ssj0058465 |
| Score | 2.4391055 |
| Snippet | P237; 在显著气候变化叠加人类活动干扰的背景下,可持续的自然资源管理对于精准掌握土地覆盖信息的需求不断提升.为应对地表形态的复杂性、地物类型的多样性、遥感图像特征的... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 1401 |
| Title | 面向土地覆盖精准分类的遥感特征参数优选方法 |
| URI | https://d.wanfangdata.com.cn/periodical/chxb202407013 |
| Volume | 53 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAFT databaseName: Open Access Digital Library issn: 1001-1595 databaseCode: KQ8 dateStart: 20120101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html omitProxy: true ssIdentifier: ssib005437539 providerName: Colorado Alliance of Research Libraries |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3NT9RAFG8IXLwYP4NfZA-OF7PYaTudmZNpl1ai0cQICTfSLq1cXBIXEuUkhqCc1APEKIbERM-oJ6Lhr3F35b_wvddhtyybiN68NLMzb-b93nvT9r3ZzhvLugpOsXQ8Ias0g7260NXUyXQ18VLfThN4K1Amprv3_Mlp7_aMmBka2Sl9tbS0mI7XlwfuK_kXq0Id2BV3yf6FZbuDQgWUwb5wBQvD9Vg2ZpFmeoIFDosE0zbTnAo1pmNTCG0WKRb4TPkskkyHTFMhdFgYIY2S1AQFZWhCzsKQiAOmPGShOAsEi3z8iSNDF81Cjb1gEEVMVcyUgzRaEFOPhQBDUXcb6bHJp15wdVlx5uWBW0yVMAjxBe7YUbBgApEj3wAAHEwNElojXpAshMZSi4-6QEBA4pnOQKLDMglqTBmRddBrIYYwssEedwvllRHHw6Ve3oujDXRdCMapH9WEkgoeSQVjAx55SKp-GokEhQkNDfAHq0RGBaBHRF9jQVyiIWWA1E5tEBJFQhI92pVfd7kP_hRzBA1RWI8MUkyifpTdSSRxfqkyJoALsyAgBBJlwKaYBTQgTpl4EG6JvMDCg-H2QwK44Phxgvu_qvkotcTRjZQ2aY7uDSUP3bRQX0xTQI-3n8SfhZBHaYzYGu8cYHF87dq8tO6PmdKqEHmIsuNSZNk2D2hZ8kJw0aTk0XKv2M581FvSniR3KbhVezCOtxBewKkt0nX0JaKvzz9JkQacBDwmfMQBPwoPy7lzvxzQQTilygEDvN9LCRGF50rRy0OMp114fi9hqeCudH3dXcDA6EjQ9ypGfLMHE4HfGASbtl428qTxsBQlTJ2yTprwvhIUz-rT1tDy_BlrNGjiH44Lj55WrlWoXKwnN89aN_c_fGy9ftPa2m5t7fz6vNZ5v9n5utd6sdZ6udb58r3zbnV_5VN7dbuzvtvaW2m9et7e2Pn54-3-s_X25m7728Y5azqOpmqTVXOmTbXJ8TPgLLPtepLlbmpnOUjqpnWb53NCpJixwBNJxt3Ex5RjmZskSZ6ktkrdjOcQaKsc9HPeGm4sNLJRq-LPKaFBZ2AU7eW5SDm4qlxIv56kSTrHL1hjRhez5p3VnD1kw4t_Irhkneg9Vy9bw4uPl7IrEIMtpmNk9t9tigqD |
| linkProvider | Colorado Alliance of Research Libraries |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E9%9D%A2%E5%90%91%E5%9C%9F%E5%9C%B0%E8%A6%86%E7%9B%96%E7%B2%BE%E5%87%86%E5%88%86%E7%B1%BB%E7%9A%84%E9%81%A5%E6%84%9F%E7%89%B9%E5%BE%81%E5%8F%82%E6%95%B0%E4%BC%98%E9%80%89%E6%96%B9%E6%B3%95&rft.jtitle=%E6%B5%8B%E7%BB%98%E5%AD%A6%E6%8A%A5&rft.au=%E9%99%88%E8%B6%85&rft.au=%E6%A2%81%E9%94%A6%E6%B6%9B&rft.au=%E6%9D%A8%E5%88%9A&rft.au=%E5%AD%99%E4%BC%9F%E4%BC%9F&rft.date=2024-08-12&rft.pub=%E6%B5%99%E6%B1%9F%E6%B5%B7%E6%B4%8B%E5%A4%A7%E5%AD%A6%E6%B5%B7%E6%B4%8B%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8A%80%E6%9C%AF%E5%AD%A6%E9%99%A2%2C%E6%B5%99%E6%B1%9F%E8%88%9F%E5%B1%B1+316022%25%E5%AE%81%E6%B3%A2%E5%A4%A7%E5%AD%A6%E5%9C%B0%E7%90%86%E4%B8%8E%E7%A9%BA%E9%97%B4%E4%BF%A1%E6%81%AF%E6%8A%80%E6%9C%AF%E7%B3%BB%2C%E6%B5%99%E6%B1%9F%E5%AE%81%E6%B3%A2+315211%25%E6%B5%99%E6%B1%9F%E6%B5%B7%E6%B4%8B%E5%A4%A7%E5%AD%A6%E6%B5%B7%E6%B4%8B%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8A%80%E6%9C%AF%E5%AD%A6%E9%99%A2%2C%E6%B5%99%E6%B1%9F%E8%88%9F%E5%B1%B1+316022%25%E6%B5%99%E6%B1%9F%E7%9C%81%E6%B0%B4%E6%96%87%E5%9C%B0%E8%B4%A8%E5%B7%A5%E7%A8%8B%E5%9C%B0%E8%B4%A8%E5%A4%A7%E9%98%9F%2C%E6%B5%99%E6%B1%9F%E5%AE%81%E6%B3%A2+315012&rft.issn=1001-1595&rft.volume=53&rft.issue=7&rft.spage=1401&rft.epage=1416&rft_id=info:doi/10.11947%2Fj.AGCS.2024.20230327&rft.externalDocID=chxb202407013 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fchxb%2Fchxb.jpg |