中文    English
当前位置: 本站首页 » 科学研究 » 科研成果 » 正文

张彤--Multiclass Labeling of Very High-Resolution Remote Sensing Imagery by Enforcing Nonlocal Shared Constraints in Multilevel

发布日期:2016-11-30 09:53:56 阅读次数:[1631]次 作者:

核心提示:来源出版物: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING

标题: Multiclass Labeling of Very High-Resolution Remote Sensing Imagery by Enforcing Nonlocal Shared Constraints in Multilevel Conditional Random Fields Model
作者: Zhang, T (Zhang, Tong); Yan, WJ (Yan, Wenjie); Li, J (Li, Jing); Chen, J (Chen, Jie)
来源出版物: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING  卷: 9  期: 7  特刊: SI  页: 2854-2867  DOI: 10.1109/JSTARS.2015.2510367  出版年: JUL 2016
摘要: In this study, we investigate the problem of multi-class pixel labeling of very high-resolution (VHR) optical remote sensing images. We propose a novel higher order potential function based on nonlocal shared constraints within the framework of a three-level conditional random field (CRF) model. The proposed approach combines classification knowledge discovery from labeled data with unsupervised segmentation cues derived from the cosegmentation of test data. The cosegmentation of unannotated test data incorporates nonlocal constraints, which are encoded in a novel truncated robust consistency potential function. The class labels are then updated iteratively by alternating between estimating semantic segmentations using CRF and integrating cosegmentation-derived labels in higher order potential functions to refine labeling results. We experimentally demonstrate the improved labeling accuracy of our approach compared with state-of-the-art multilevel CRF approaches based on quantitative and qualitative results. We also show that our approach can address the issue of lacking accurately labeled training data.


版权所有:测绘遥感信息工程国家重点实验室   
联系地址: 中国·武汉市珞瑜路129号   邮编: 430079   E-mail:liesmars@whu.edu.cn
Tel/Fax:027-68778969(办公室) 027-68778229(国际交流办公室)027-68778525(研究生管理办公室)