Stereo matching cost computation based on nonsubsampled contourlet transform

被引：9
作者：
Zhang, Ka [1 ,2 ,3 ]
Sheng, Yehua [1 ,2 ,3 ]
Lv, Haiyang [1 ]
机构：
[1] Nanjing Normal Univ, Key Lab Virtual Geog Environm, Minist Educ, Nanjing 210023, Jiangsu, Peoples R China
[2] Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Jiangsu, Peoples R China
[3] Nanjing Normal Univ, Key Lab Police Geog Informat Technol, Minist Publ Secur, Nanjing 210023, Jiangsu, Peoples R China
来源：
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION | 2015年 / 26卷
基金：
中国国家自然科学基金;
关键词：
Stereo image matching; Nonsubsampled contourlet transform; Feature vector; Weighted matching cost; Matching accuracy; POINT CLOUDS; REGISTRATION; IMAGES; ROBUST;
D O I：
10.1016/j.jvcir.2014.10.002
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A new matching cost computation method based on nonsubsampled contourlet transform (NSCT) for stereo image matching is proposed in this paper. Firstly, stereo image is decomposed into high frequency sub-band images at different scales and along different directions by NSCT. Secondly, by utilizing coefficients in high frequency domain and grayscales in RGB color space, the computation model of weighted matching cost between two pixels is designed based on the gestalt laws. Lastly, two types of experiments are carried out with standard stereopairs in the Middlebury benchmark. One of the experiments is to confirm optimum values of NSCT scale and direction parameters, and the other is to compare proposed matching cost with nine known matching costs. Experimental results show that the optimum values of scale and direction parameters are respectively 2 and 3, and the matching accuracy of the proposed matching cost is twice higher than that of traditional NCC cost. (C) 2014 Elsevier Inc. All rights reserved.
引用
收藏
页码：275 / 283
页数：9
相关论文
共 24 条
  • [1] Accurate hardware-based stereo vision
    Ambrosch, Karina
    Kubinger, Wilfried
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2010, 114 (11) : 1303 - 1316
  • [2] [Anonymous], 2012, J TELECOMMUN ELECT C
  • [3] [Anonymous], P IEEE C COMP VIS PA
  • [4] Neural adaptive stereo matching
    Binaghi, E
    Gallo, I
    Marino, G
    Raspanti, M
    [J]. PATTERN RECOGNITION LETTERS, 2004, 25 (15) : 1743 - 1758
  • [5] Robust affine invariant feature extraction for image matching
    Cheng, Liang
    Gong, Jianya
    Yang, Xiaoxia
    Fan, Chong
    Han, Peng
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2008, 5 (02) : 246 - 250
  • [6] The nonsubsampled contourlet transform: Theory, design, and applications
    da Cunha, Arthur L.
    Zhou, Jianping
    Do, Minh N.
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2006, 15 (10) : 3089 - 3101
  • [7] Dense stereo correspondence with slanted surface using phase-based algorithm
    El-Etriby, Sherif
    Al-Hamadi, Ayoub K.
    Michaelis, Bernd
    [J]. 2007 IEEE INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS, PROCEEDINGS, VOLS 1-8, 2007, : 1807 - 1813
  • [8] Fusion of airborne laserscanning point clouds and images for supervised and unsupervised scene classification
    Gerke, Markus
    Xiao, Jing
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 87 : 78 - 92
  • [9] A performance study on different cost aggregation approaches used in real-time stereo matching
    Gong, Minglun
    Yang, Ruigang
    Wang, Liang
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2007, 75 (02) : 283 - 296
  • [10] 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
123