Impervious surface extraction using coupled spectral-spatial features

	Impervious surface extraction using coupled spectral-spatial features
	Yu, Xinju 1; Shen, Zhanfeng 1; Cheng, Xi 1; Xia, Liegang 1; Luo, Jiancheng 1
刊名	Journal of Applied Remote Sensing
	2016
卷号	10 期号:3
关键词	SUPPORT VECTOR MACHINES OBJECT DETECTION BAG REPRESENTATION FUSION KERNEL SCALE
通讯作者	Shen, Zhanfeng (shenzf@radi.ac.cn)
英文摘要	Accurate extraction of urban impervious surface data from high-resolution imagery remains a challenging task because of the spectral heterogeneity of complex urban land-cover types. Since the high-resolution imagery simultaneously provides plentiful spectral and spatial features, the accurate extraction of impervious surfaces depends on effective extraction and integration of spectral-spatial multifeatures. Different features have different importance for determining a certain class; traditional multifeature fusion methods that treat all features equally during classification cannot utilize the joint effect of multifeatures fully. A fusion method of distance metric learning (DML) and support vector machines is proposed to find the impervious and pervious subclasses from Chinese ZiYuan-3 (ZY-3) imagery. In the procedure of finding appropriate spectral and spatial feature combinations with DML, optimized distance metric was obtained adaptively by learning from the similarity side-information generated from labeled samples. Compared with the traditional vector stacking method that used each feature equally for multifeatures fusion, the approach achieves an overall accuracy of 91.6% (4.1% higher than the prior one) for a suburban dataset, and an accuracy of 92.7% (3.4% higher) for a downtown dataset, indicating the effectiveness of the method for accurately extracting urban impervious surface data from ZY-3 imagery. © 2016 Society of Photo-Optical Instrumentation Engineers (SPIE).
学科主题	Environmental Sciences & Ecology; Remote Sensing; Imaging Science & Photographic Technology
类目[WOS]	Environmental Sciences ; Remote Sensing ; Imaging Science & Photographic Technology
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:20163402732790
内容类型	期刊论文
源URL	[http://ir.radi.ac.cn/handle/183411/39377]
专题	遥感与数字地球研究所_SCI/EI期刊论文_期刊论文
作者单位	1. Chinese Academy of Sciences, Institute of Remote Sensing and Digital Earth, Beijing 2.100101, China 3. Chengdu University of Technology, School of Geophysics, Chengdu 4.610059, China 5. Zhejiang University of Technology, College of Computer Science and Technology, Hangzhou 6.310014, China
推荐引用方式 GB/T 7714	Yu, Xinju,Shen, Zhanfeng,Cheng, Xi,et al. Impervious surface extraction using coupled spectral-spatial features[J]. Journal of Applied Remote Sensing,2016,10(3).
APA	Yu, Xinju,Shen, Zhanfeng,Cheng, Xi,Xia, Liegang,&Luo, Jiancheng.(2016).Impervious surface extraction using coupled spectral-spatial features.Journal of Applied Remote Sensing,10(3).
MLA	Yu, Xinju,et al."Impervious surface extraction using coupled spectral-spatial features".Journal of Applied Remote Sensing 10.3(2016).