Image Segmentation Based on Constrained Spectral Variance Difference and Edge Penalty

Remote Sensing

Bo Chen³  Fang Qiu²  Bingfang Wu³  Hongyue Du¹  Ioannis Gitas⁴ 

[1] China Mapping Technology Service Corporation, Beijing 100088, China; E-Mail:;Geospatial Information Sciences, University of Texas at Dallas, Dallas, TX 75080, USA;Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China; E-Mails:Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China;

关键词: remote sensing image segmentation;    region merging;    multi-scale;    constrained spectral variance difference;    edge penalty;   

DOI  :  10.3390/rs70505980

来源: mdpi

【 摘 要 】

Segmentation, which is usually the first step in object-based image analysis (OBIA), greatly influences the quality of final OBIA results. In many existing multi-scale segmentation algorithms, a common problem is that under-segmentation and over-segmentation always coexist at any scale. To address this issue, we propose a new method that integrates the newly developed constrained spectral variance difference (CSVD) and the edge penalty (EP). First, initial segments are produced by a fast scan. Second, the generated segments are merged via a global mutual best-fitting strategy using the CSVD and EP as merging criteria. Finally, very small objects are merged with their nearest neighbors to eliminate the remaining noise. A series of experiments based on three sets of remote sensing images, each with different spatial resolutions, were conducted to evaluate the effectiveness of the proposed method. Both visual and quantitative assessments were performed, and the results show that large objects were better preserved as integral entities while small objects were also still effectively delineated. The results were also found to be superior to those from eCongnition’s multi-scale segmentation.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.