A scale self-adapting segmentation approach and knowledge transfer for automatically updating land use/cover change databases using high spatial resolution images
文献类型：期刊论文
| 作者 | Wang, Zhihua1,3; Yang, Xiaomei1,2; Lu, Chen1,3; Yang, Fengshuo1,3 |
| 刊名 | INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
 |
| 出版日期 | 2018-07-01 |
| 卷号 | 69页码:88-98 |
| 关键词 | Ocean disaster Coastal area Land use/cover change High spatial resolution images GEOBIA Scale issue |
| ISSN号 | 0303-2434 |
| DOI | 10.1016/j.jag.2018.03.001 |
| 通讯作者 | Yang, Xiaomei(yangxm@lreis.ac.cn) |
| 英文摘要 | Automatic updating of land use/cover change (LUCC) databases using high spatial resolution images (HSRI) is important for environmental monitoring and policy making, especially for coastal areas that connect the land and coast and that tend to change frequently. Many object-based change detection methods are proposed, especially those combining historical LUCC with HSRI. However, the scale parameter(s) segmenting the serial temporal images, which directly determines the average object size, is hard to choose without experts' intervention. And the samples transferred from historical LUCC also need experts' intervention to avoid insufficient or wrong samples. With respect to the scale parameter(s) choosing, a Scale Self-Adapting Segmentation (SSAS) approach based on the exponential sampling of a scale parameter and location of the local maximum of a weighted local variance was proposed to determine the scale selection problem when segmenting images constrained by LUCC for detecting changes. With respect to the samples transferring, Knowledge Transfer (KT), a classifier trained on historical images with LUCC and applied in the classification of updated images, was also proposed. Comparison experiments were conducted in a coastal area of Zhujiang, China, using SPOT 5 images acquired in 2005 and 2010. The results reveal that (1) SSAS can segment images more effectively without intervention of experts. (2) KT can also reach the maximum accuracy of samples transfer without experts' intervention. Strategy SSAS + KT would be a good choice if the temporal historical image and LUCC match, and the historical image and updated image are obtained from the same resource. |
| WOS关键词 | REMOTE-SENSING IMAGES ; ACCURACY ASSESSMENT MEASURES ; OBJECT-BASED CLASSIFICATION ; CHANGE-VECTOR ANALYSIS ; COVER CHANGE ; MULTISCALE SEGMENTATION ; PARAMETER SELECTION ; SATELLITE IMAGES ; DISCREPANCY MEASURE ; TIME-SERIES |
| 资助项目 | National Key Research and Development Program of China[2016YFC1402003] ; National Science Foundation of China[41671436] ; National Science Foundation of China[41421001] ; Innovation Project of LREIS[O88RAA01YA] |
| WOS研究方向 | Remote Sensing |
| 语种 | 英语 |
| WOS记录号 | WOS:000431156700008 |
| 出版者 | ELSEVIER SCIENCE BV |
| 资助机构 | National Key Research and Development Program of China ; National Science Foundation of China ; Innovation Project of LREIS |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/54980]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Yang, Xiaomei |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, 11A Datun Rd, Beijing 100101, Peoples R China 2.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing, Jiangsu, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Zhihua,Yang, Xiaomei,Lu, Chen,et al. A scale self-adapting segmentation approach and knowledge transfer for automatically updating land use/cover change databases using high spatial resolution images[J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,2018,69:88-98. |
| APA | Wang, Zhihua,Yang, Xiaomei,Lu, Chen,&Yang, Fengshuo.(2018).A scale self-adapting segmentation approach and knowledge transfer for automatically updating land use/cover change databases using high spatial resolution images.INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,69,88-98. |
| MLA | Wang, Zhihua,et al."A scale self-adapting segmentation approach and knowledge transfer for automatically updating land use/cover change databases using high spatial resolution images".INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 69(2018):88-98. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。