A novel multi-scale relative salience feature for remote sensing image analysis

ISCAS OpenIR

	A novel multi-scale relative salience feature for remote sensing image analysis
	Huang, Zhijian (1); Zhang, Jinfang (2); Xu, Fanjiang (2); Huang, Z.(zhijian07@iscas.ac.cn)
	2014
发表期刊	Optik
ISSN	304026
卷号	125 期号:1 页码:516-520
摘要	This paper presents a novel feature for remote sensing image analysis, called multi-scale relative salience (MsRS) feature. It is constructed by modeling the process of feature value changing with scales. Firstly, the multi-scale observation values at each site are obtained by convolved with recursive Gaussian filters for efficiency. Secondly, the multi-scale observation values are compared with the initial value to generate the relative salience. Lastly, the relative salience between multi-scales are embed into a single feature called the MsRS. The scale in MsRS has explicit spatial meaning which is convenient to choose appropriate scale for specified object. In the MsRS map, the inner of each object become more consistent, while the contrast between object and background is enlarged. The MsRS can be used as preprocessing step of many applications, such as segmentation. Two state-of-art segmentations (the mean shift and the statistical region merging) are taken into experiments and the results proved that it brings improvement obviously. © 2013 Elsevier GmbH.; This paper presents a novel feature for remote sensing image analysis, called multi-scale relative salience (MsRS) feature. It is constructed by modeling the process of feature value changing with scales. Firstly, the multi-scale observation values at each site are obtained by convolved with recursive Gaussian filters for efficiency. Secondly, the multi-scale observation values are compared with the initial value to generate the relative salience. Lastly, the relative salience between multi-scales are embed into a single feature called the MsRS. The scale in MsRS has explicit spatial meaning which is convenient to choose appropriate scale for specified object. In the MsRS map, the inner of each object become more consistent, while the contrast between object and background is enlarged. The MsRS can be used as preprocessing step of many applications, such as segmentation. Two state-of-art segmentations (the mean shift and the statistical region merging) are taken into experiments and the results proved that it brings improvement obviously. © 2013 Elsevier GmbH.
收录类别	SCI ; EI
关键词	Multi-scale Feature Mean Shift Statistical Region Merging Sift Scale Space
部门归属	(1) SPDF, School of Electronic Science and Engineering, National University of Defense Technology, China; (2) IIST Key Lab., Institute of Software, Chinese Academy of Sciences, Zhongguancun, Beijing 100190, China
语种	英语
WOS记录号	WOS:000329537300113
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16887
专题	中国科学院软件研究所
通讯作者	Huang, Z.(zhijian07@iscas.ac.cn)
推荐引用方式 GB/T 7714	Huang, Zhijian ,Zhang, Jinfang ,Xu, Fanjiang ,et al. A novel multi-scale relative salience feature for remote sensing image analysis[J]. Optik,2014,125(1):516-520.
APA	Huang, Zhijian ,Zhang, Jinfang ,Xu, Fanjiang ,&Huang, Z..(2014).A novel multi-scale relative salience feature for remote sensing image analysis.Optik,125(1),516-520.
MLA	Huang, Zhijian ,et al."A novel multi-scale relative salience feature for remote sensing image analysis".Optik 125.1(2014):516-520.