1. Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
2. Shandong Univ Sci & Technol, Coll Geomat, Qingdao 266590, Peoples R China
折叠
Abstract
Image segmentation is a key issue in geographic object-based image analysis, thus determining the appropriate segmentation parameter is a prerequisite to allowing for obtaining accurate segmentation. In this study, an unsupervised segmentation parameter selection method using the local spatial statistics was proposed for achieving the automatic parameter optimization of image segmentation. The two measure of within-segment homogeneity (WSH) and between-segment heterogeneity (BSH) were calculated using local spatial statistics approach, and then integrated into a global value for indicating the overall segmentation quality. In addition, the contribution of the common boundary between each segment and one of its neighboring segments was considered in BSH calculation for obtaining a more objective evaluation. For this experiment, the multi-resolution segmentation (MRS) method was used as a segmentation algorithm and GF-1 image used as test data. The measure analysis experiment of the proposed method showed BSH is more sensitive to under-segmentation. The visual and discrepancy measures results of the proposed method compared with the other four methods revealed that the proposed method is more potential to recognize the proper segmentation parameter with the purpose of allowing for obtaining segmentations with high quality.
NSTL
Elsevier