Feature Selection Solution with High Dimensionality and Low-Sample Size for Land Cover Classification in Object-Based Image Analysis
文献类型：期刊论文
| 作者 | Huang, Yaohuan1,2; Zhao, Chuanpeng1,2; Yang, Haijun3; Song, Xiaoyang4; Chen, Jie1; Li, Zhonghua1,2 |
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2017-09-01 |
| 卷号 | 9期号:9页码:16 |
| ISSN号 | 2072-4292 |
| 关键词 | feature selection generalized partial least squares regression small samples land cover OBIA |
| DOI | 10.3390/rs9090939 |
| 通讯作者 | Zhao, Chuanpeng(zhaocp.15s@igsnrr.ac.cn) ; Song, Xiaoyang(songxiaoyang.good@163.com) |
| 英文摘要 | Land cover information extraction through object-based image analysis (OBIA) has become an important trend in remote sensing, thanks to the increasing availability of high-resolution imagery. Segmented objects have a large number of features that cause high-dimension and low-sample size problems in the classification process. In this study, on the basis of a partial least squares generalized linear regression (PLSGLR), we propose a group corrected PLSGLR, known as G-PLSGLR, that aims to reduce the redundancy of object features for land cover identifications. Using Gaofen-2 images, the area of interest was segmented and sampled to generate small sample-size training datasets with 51 object features. The features selected by G-PLSGLR were compared against a guided regularized random forest (GRRF) in metrics of reduction rate, feature redundancy, and accuracy assessment of classification. Three indicators of overall accuracy (OA), user's accuracy (UA), and producer's accuracy (PA) were applied for accuracy assessment in this paper. The result shows that the G-PLSGLR achieved a reduction rate of 9.27 with a feature redundancy of 0.29, and a value of OA 90.63%. The GRRF achieved a reduction rate of 1.61 with a feature redundancy of 0.42, and a value of OA 85.56%. The PA of each land cover category was more than 95% using features selected by G-PLSGLR, while the PA ranged from 77 to 96% using features selected by GRRF. The UA of G-PLSGLR-selected features ranged from 70 to 80% except for grass land and bare land, which achieved 10% higher UA than GRRF-selected features. The G-PLSGLR method we proposed has the advantages of a large reduction rate, low feature redundancy, and high classification performance, which can be applied in OBIA-based land cover classification. |
| WOS关键词 | PARTIAL LEAST-SQUARES ; HYPERSPECTRAL DATA ; FOREST ; ALGORITHMS ; CHINA |
| 资助项目 | National Key Research and Development Program of China[2017YFB0503005] ; National Key Research and Development Program of China[2016YFC0401404] ; National Natural Science Foundation of China[51309210] |
| WOS研究方向 | Remote Sensing |
| 语种 | 英语 |
| 出版者 | MDPI AG |
| WOS记录号 | WOS:000414138700069 |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/61171]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Zhao, Chuanpeng; Song, Xiaoyang |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Univ Chinese Acad Sci, Coll Resource & Environm, Beijing 100049, Peoples R China 3.State Environm Protect Key Lab Satellite Remote S, Beijing 100094, Peoples R China 4.China Univ Min & Technol, Coll Geosci & Surveying Engn, Beijing 100083, Peoples R China |
| 推荐引用方式 GB/T 7714 | Huang, Yaohuan,Zhao, Chuanpeng,Yang, Haijun,et al. Feature Selection Solution with High Dimensionality and Low-Sample Size for Land Cover Classification in Object-Based Image Analysis[J]. REMOTE SENSING,2017,9(9):16. |
| APA | Huang, Yaohuan,Zhao, Chuanpeng,Yang, Haijun,Song, Xiaoyang,Chen, Jie,&Li, Zhonghua.(2017).Feature Selection Solution with High Dimensionality and Low-Sample Size for Land Cover Classification in Object-Based Image Analysis.REMOTE SENSING,9(9),16. |
| MLA | Huang, Yaohuan,et al."Feature Selection Solution with High Dimensionality and Low-Sample Size for Land Cover Classification in Object-Based Image Analysis".REMOTE SENSING 9.9(2017):16. |
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。