Measuring the Effectiveness of Various Features for Thematic Information Extraction From Very High Resolution Remote Sensing Imagery
Measuring the Effectiveness of Various Features for Thematic Information Extraction From Very High Resolution Remote Sensing Imagery
复制标题
测量从极高分辨率遥感图像中提取主题信息的各种特征的有效性
DOI：
10.1109/tgrs.2015.2411331
复制
发表时间：
2015-03
影响因子：
8.2
通讯作者：
Li, Deren
中科院分区：
文献类型：
--
作者：
Chen, Xi;Fang, Tao;Huo, Hong;Li, Deren
Generally, some object-based features are more relevant to a thematic class than other features. These strongly relevant features, termed as class-specific features, would significantly contribute to thematic information extraction for very high resolution (VHR) images. However, many existing feature selection methods have been designed to select a good feature subset for all classes, rather than an independent feature subset for the thematic class. The latter might better meet the requirement of thematic information extraction than the former. In addition, the lack of quantitative evaluation of the contribution of the selected features to thematic classes also weakens our understandability of these features. To address the problems, class-specific feature selection methods are developed to measure the effectiveness of features for extracting thematic information from VHR images. First, the one-versus-all scheme is combined with traditional feature selection methods, such as ReliefF and LeastC. Also, one-versus-one scheme is utilized for alleviating the negative impact of a class imbalance problem arising from the one-versus-all scheme. Then, the relative contributions of features to thematic classes are obtained by the class-specific feature selection methods to describe the effectiveness of features for thematic information extraction. Finally, the class-specific feature selection methods are compared with the original methods on three different VHR image data sets by the nearest neighbor and support vector machine. Experimental results show that the class-specific feature selection methods outperform the corresponding conventional methods, and the one-versus-one scheme surpasses one-versus-all scheme. Additionally, many features are evaluated by the class-specific feature selection methods, to provide end users advice on effectiveness of the features.
登录
查看更多内容
影响因子：
3.4
作者：
Y. Maghsoudi;M. V. Valadan Zoej;M. Collins
通讯作者：
Y. Maghsoudi;M. V. Valadan Zoej;M. Collins
分层流形学习及其在高分辨率遥感图像监督分类中的应用
影响因子：
8.2
作者：
Huang HongBing;Huo Hong;Fang Tao
通讯作者：
Fang Tao
DOI：
10.1016/s0065-2458(08)60404-0
发表时间：
1993
期刊：
Adv. Comput.
影响因子：
--
作者：
Franziska Wulf
通讯作者：
Franziska Wulf
DOI：
10.1109/cvpr.2005.16
发表时间：
2005-06
期刊：
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
影响因子：
--
作者：
Li Fei-Fei-Li-Fei-Fei-48004138;P. Perona
通讯作者：
Li Fei-Fei-Li-Fei-Fei-48004138;P. Perona
DOI：
--
发表时间：
2007
期刊：
--
影响因子：
--
作者：
Tom Fawcett
通讯作者：
Tom Fawcett