Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images

doi:10.3390/rs10081193

	Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images
	Wang, Yongji 1,2; Qi, Qingwen 1; Liu, Ying 1
刊名	REMOTE SENSING
	2018-08-01
卷号	10 期号:8 页码:24
关键词	image segmentation unsupervised evaluation remote sensing area-weighted variance Jeffries-Matusita distance geographic object-based image analysis
ISSN号	2072-4292
DOI	10.3390/rs10081193
通讯作者	Qi, Qingwen(qiqw@igsnrr.ac.cn)
英文摘要	Image segmentation is an important process and a prerequisite for object-based image analysis. Thus, evaluating the performance of segmentation algorithms is essential to identify effective segmentation methods and to optimize the scale. In this paper, we propose an unsupervised evaluation (UE) method using the area-weighted variance (WV) and Jeffries-Matusita (JM) distance to compare two image partitions to evaluate segmentation quality. The two measures were calculated based on the local measure criteria, and the JM distance was improved by considering the contribution of the common border between adjacent segments and the area of each segment in the JM distance formula, which makes the heterogeneity measure more effective and objective. Then the two measures were presented as a curve when changing the scale from 8 to 20, which can reflect the segmentation quality in both over- and under-segmentation. Furthermore, the WV and JM distance measures were combined by using three different strategies. The effectiveness of the combined indicators was illustrated through supervised evaluation (SE) methods to clearly reveal the segmentation quality and capture the trade-off between the two measures. In these experiments, the multiresolution segmentation (MRS) method was adopted for evaluation. The proposed UE method was compared with two existing UE methods to further confirm their capabilities. The visual and quantitative SE results demonstrated that the proposed UE method can improve the segmentation quality.
资助项目	Science and Technology Service Network Project[KFJ-EW-STS-069] ; Special Topic of Basic Work of Science and Technology[2007FY140800]
WOS关键词	PARAMETER OPTIMIZATION ; SCALE PARAMETER ; MULTIRESOLUTION ; CLASSIFICATION ; LANDSCAPES ; ALGORITHMS ; WATERSHEDS ; EXTRACTION ; SELECTION ; ACCURACY
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000443618100029
资助机构	Science and Technology Service Network Project ; Special Topic of Basic Work of Science and Technology
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/54277]
专题	中国科学院地理科学与资源研究所
通讯作者	Qi, Qingwen
作者单位	1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yongji,Qi, Qingwen,Liu, Ying. Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images[J]. REMOTE SENSING,2018,10(8):24.
APA	Wang, Yongji,Qi, Qingwen,&Liu, Ying.(2018).Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images.REMOTE SENSING,10(8),24.
MLA	Wang, Yongji,et al."Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images".REMOTE SENSING 10.8(2018):24.