Real-Time Stereo Matching on CUDA Using an Iterative Refinement Method for Adaptive Support-Weight Correspondences

被引：87
作者：
Kowalczuk, Jedrzej [1 ]
Psota, Eric T. [1 ]
Perez, Lance C. [1 ]
机构：
[1] Univ Nebraska, Dept Elect Engn, Lincoln, NE 68588 USA
来源：
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY | 2013年 / 23卷 / 01期
关键词：
Adaptive support weights; CUDA; iterative refinement; real-time stereo matching; BELIEF PROPAGATION;
D O I：
10.1109/TCSVT.2012.2203200
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
High-quality real-time stereo matching has the potential to enable various computer vision applications including semi-automated robotic surgery, teleimmersion, and 3-D video surveillance. A novel real-time stereo matching method is presented that uses a two-pass approximation of adaptive support-weight aggregation, and a low-complexity iterative disparity refinement technique. Through an evaluation of computationally efficient approaches to adaptive support-weight cost aggregation, it is shown that the two-pass method produces an accurate approximation of the support weights while greatly reducing the complexity of aggregation. The refinement technique, constructed using a probabilistic framework, incorporates an additive term into matching cost minimization and facilitates iterative processing to improve the accuracy of the disparity map. This method has been implemented on massively parallel high-performance graphics hardware using the Compute Unified Device Architecture computing engine. Results show that the proposed method is the most accurate among all of the real-time stereo matching methods listed on the Middlebury stereo benchmark.
引用
收藏
页码：94 / 104
页数：11
相关论文
共 25 条
  • [1] [Anonymous], 2011, NVIDIA CUDA C PROGRA
  • [2] Bleyer M, 2010, PROC CVPR IEEE, P1570, DOI 10.1109/CVPR.2010.5539783
  • [3] Carreira-Perpinan M.A., 2006, IEEE Comp Soc Conf Comp Vis Patt Recog, P1160, DOI DOI 10.1109/CVPR.2006.44
  • [4] Efficient stereo with multiple windowing
    Fusiello, A
    Roberto, V
    Trucco, E
    [J]. 1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, : 858 - 863
  • [5] Grauer-Gray S., 2009, Proc. IEEE WACV, P1
  • [6] LOCAL STEREO MATCHING USING GEODESIC SUPPORT WEIGHTS
    Hosni, Asmaa
    Bleyer, Michael
    Gelautz, Margrit
    Rhemann, Christoph
    [J]. 2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, : 2093 - 2096
  • [7] KANG SB, 2001, PROC CVPR IEEE, P103, DOI DOI 10.HTTP://WWW.10.1109/CVPR.2001.990462
  • [8] Klaus A, 2006, INT C PATT RECOG, P15
  • [9] Kolmogorov V, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, P508, DOI 10.1109/ICCV.2001.937668
  • [10] Mattoccia Stefano, 2009, Computer Vision - ACCV 2009. 9th Asian Conference on Computer Vision. Revised Selected Papers, P371
123