CORC  > 北京大学  > 信息科学技术学院
COST-VOLUME FILTERING-BASED STEREO MATCHING WITH IMPROVED MATCHING COST AND SECONDARY REFINEMENT
Jiao, Jianbo ; Wang, Ronggang ; Wang, Wenmin ; Dong, Shengfu ; Wang, Zhenyu ; Gao, Wen
2014
关键词Local stereo cost-volume filtering matching cost disparity refinement ALGORITHM
英文摘要Recent cost-volume filtering-based local stereo methods have achieved comparable accuracy with global methods. However, there are still some significant outliers existing in the final disparity map. In this paper, we propose a cost-volume filtering-based local stereo matching method that employs a new combined cost and a novel secondary disparity refinement mechanism. The combined cost is formulated by a modified color census transform, truncated absolute differences of color and gradients. Symmetric guided filter is used for the cost aggregation. Different from traditional stereo matching, a novel secondary disparity refinement is proposed to further remove remaining outliers. Experimental results on Middlebury benchmark show that our method ranks the 5th out of the 144 submitted methods, and is the best cost-volume filtering-based local method. Furthermore, experiments on real world sequences also validate the effectiveness of our proposed method.; EI; CPCI-S(ISTP); jianbojiao@sz.pku.edu.cn; rgwang@pkusz.edu.cn; wangwenmin@pkusz.edu.cn; dongsf@pkusz.edu.cn; wangzhenyu@pkusz.edu.cn; wgao@pku.edu.cn; Septmber; 2014-September
语种英语
出处2014 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)
DOI标识10.1109/ICME.2014.6890201
内容类型其他
源URL[http://ir.pku.edu.cn/handle/20.500.11897/423997]  
专题信息科学技术学院
推荐引用方式
GB/T 7714
Jiao, Jianbo,Wang, Ronggang,Wang, Wenmin,et al. COST-VOLUME FILTERING-BASED STEREO MATCHING WITH IMPROVED MATCHING COST AND SECONDARY REFINEMENT. 2014-01-01.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace