Local Stereo Matching with Improved Matching Cost and Disparity Refinement

被引:57
作者
Jiao, Jianbo [1 ]
Wang, Ronggang [1 ]
Wang, Wenmin [1 ,2 ]
Dong, Shengfu [1 ]
Wang, Zhenyu [1 ]
Gao, Wen [1 ]
机构
[1] Peking Univ, Shenzhen Grad Sch, Beijing, Peoples R China
[2] Peking Univ, Shenzhen Grad Sch, Sch Elect & Comp Engn, Beijing, Peoples R China
基金
美国国家科学基金会;
关键词
Benchmark testing; Disparity refinement; Image color analysis; Image edge detection; Matching cost; Multimedia; Radar; Research and development; Stereo matching; Stereo vision; Transforms;
D O I
10.1109/MMUL.2014.51
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
A local stereo matching method that uses combined cost and a novel secondary disparity refinement mechanism ranked fifth out of the 153 methods submitted for the Middlebury benchmark.
引用
收藏
页码:16 / 27
页数:12
相关论文
共 19 条
[2]   Mean shift: A robust approach toward feature space analysis [J].
Comaniciu, D ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619
[3]   Domain Transformation-Based Efficient Cost Aggregation for Local Stereo Matching [J].
Cuong Cao Pham ;
Jeon, Jae Wook .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 23 (07) :1119-1130
[4]  
De-Maeztu L, 2011, IEEE I CONF COMP VIS, P1708, DOI 10.1109/ICCV.2011.6126434
[5]   Color invariance [J].
Geusebroek, JM ;
van den Boomgaard, R ;
Smeulders, AWM ;
Geerts, H .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (12) :1338-1350
[6]  
Jiao JB, 2014, IEEE INT CON MULTI
[7]  
Kolmogorov V, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, P508, DOI 10.1109/ICCV.2001.937668
[8]  
Mei X, 2011, PROC CVPR IEEE, P1257
[9]  
Pei SC, 2013, I SYMP CONSUM ELECTR, P209
[10]  
Pham C., 2013, IEEE T CIRC SYST VID, V23