Please wait a minute...
J4  2011, Vol. 45 Issue (9): 1636-1642    DOI: 10.3785/j.issn.1008-973X.2011.09.021
    
Mutual information based non-parametric
transform stereo matching algorithm
LAI Xiao-bo , ZHU Shi-qiang
State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

Aiming at the limitations of the weak real-time and the low reliability in the traditional non-parametric transform stereo matching algorithms, a mutual information based non-parametric transform stereo matching algorithm was proposed. Gray values of all the pixels in the transform window were averaged, and then the mean value was taken as the gray value of the center pixel. In order to take the pixels' mutual information into consideration while finding stereo correspondence, the original gray value of the neighborhood pixels whose the relative position was one unit greater than that of the center pixel was replaced by the gray value through bilinear interpolation. The non-parametric transform of the gray values of the pixels in the transform window was implemented, and a dense map was obtained. The experimental results indicate that compared with other single area-based matching algorithms, the percentage of bad matching pixels is nearly equivalent to other algorithms while it can improve the robustness of the traditional non-parametric transform stereo matching approaches effectively.



Published: 01 September 2011
CLC:  TP 391.41  
Cite this article:

LAI Xiao-bo , ZHU Shi-qiang. Mutual information based non-parametric
transform stereo matching algorithm. J4, 2011, 45(9): 1636-1642.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2011.09.021     OR     https://www.zjujournals.com/eng/Y2011/V45/I9/1636


基于互相关信息的非参数变换立体匹配算法

针对传统的非参数变换立体匹配算法实时性不强和可靠性不高的局限性,提出一种基于互相关信息的非参数变换立体匹配算法.将变换窗口内所有像素的灰度值进行平均,然后将平均值作为中心像素的灰度值;为了在立体匹配时能够考虑像素间的互相关信息,将变换窗口各邻域与中心像素的相对位置大于一个单位的像素,其灰度值用双线性插值后的灰度值替代;将变换窗口的像素灰度值进行非参数变换立体匹配,得到致密的视差图.实验结果表明:与其他基于局部的单一立体匹配算法相比,该算法得到的误匹配像素百分比与其他算法相当,能够有效提高传统非参数变换立体匹配算法的鲁棒性.

[1] SCHARSTEIN D, SZELISKI R. A taxonomy and evaluation of dense two_frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(1/2/3): 7-42.
[2] ZITNICK C L, KANG S B. Stereo for imagebased rendering using image oversegmentation[J]. International Journal of Computer Vision, 2007, 75(1): 49-65.
[3] KLAUS A, SORMANN A, KAMER K. Segmentbased Stereo matching using belief propagation and a selfadapting dissimilarity measure[C]∥IEEE International Conference on Pattern Recognition. Hong Kong:IEEE, 2006: 15-18.
[4] 管业鹏, 顾伟康. 基于灰度相关复峰集立体匹配法[J]. 浙江大学学报: 工学版, 2005, 39(4): 522-525.
GUAN Yepeng, GU Weikang. Gray correlation multipeak set based stereo matching algorithm[J]. Journal of Zhejiang University: Engineering Science, 2005, 39(4): 522-525.
[5] BIRCHFIELD S, TOMASI C. A pixel dissimilarity measure that is insensitive to image sampling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(4): 401-406.
[6] VEKSLER O. Stereo correspondence by dynamic programming on a tree[C]∥IEEE International Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005, 2: 384-390.
[7] WANG L, LIAO M, GONG M, et al. Highquality realtime stereo using adaptive cost aggregation and dynamic programming[C]∥Proceedings of Third International Symposium on 3D Data Processing, Visualization, and Transmission. Chapel Hill: IEEE, 2006: 798-805.
[8] 郭大波, 卢朝阳, 焦卫东, 等. 遮挡检测/立体匹配中的分段动态规划法[J]. 电子学报, 2009, 37(7): 1516-1520.
GUO Dabo, LU Zhaoyang, JIAO Weidong, et al. Dynamic programming in segments for occlusion detection/stereo matching[J]. ACTA ELECTRONICA SINICA, 2009, 37(7): 1516-1520.
[9] KOLMOGOROV V, ZABIH R. Computing visual correspondence with occlusions using graph cuts[C]∥IEEE International Conference on Computer Vision. Vancouver: IEEE, 2001: 508-515.
[10] 张令涛, 曲道奎, 徐方. 一种基于图割的改进立体匹配算法[J]. 机器人, 2010, 32(1): 104-108.
ZHANG Lingtao, QU Daokui, XU Fang. An improved stereo matching algorithm based on graph cuts[J]. Robot, 2010, 32(1): 104-108.
[11] YANG Q, WANG L, AHUJA N. A constantspace belief propagation algorithm for stereo matching[C]∥IEEE International Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 298-305.
[12] 徐彦泓, 朱云芳, 杜歆, 等. 非参数立体匹配算法的FPGA实现[J]. 浙江大学学报: 工学版, 2009, 43(2): 250-254.
XU Yanhong, ZHU Yunfang, DU Xin, et al. FPGA implementation of nonparametric stereo matching algorithm[J]. Journal of Zhejiang University: Engineering Science, 2009, 43(2): 250-254.
[13] ZABIH R, WOODFILL J. Nonparametric local transforms for computing visual correspondence[C]∥IEEE International Conference on Computer Vision. Vancouver: IEEE, 1994: 151-158.
[14] HIRSCHMULLER H. Stereo processing by semiglobal matching and mutual information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 328-341.
[15] NALPANTIDIS L, GASTERATOS A. Stereo vision for robotic applications in the presence of nonideal lighting conditions[J]. Image and Vision Computing, 2010, 28(6): 940-951.
[16] WANG Z, ZHENG Z. A region based stereo matching algorithm using cooperative optimization[C]∥IEEE International Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 1-8.
[17] OLAGUE G, FEMANDEZ F, PEREZ C B, et al. The infection algorithm: an artificial epidemic approach for dense stereo correspondence[J]. Springer Berlin, 2006, 3242: 622-632.

[1] YANH Yu-ting, SHI Yu-hui, XIA Shun-ren. Discussion mechanism based brain storm optimization algorithm[J]. J4, 2013, 47(10): 1705-1711.
[2] ZHU Xiao-en, HAO Xin, XIA Shun-ren. Feature selection algorithm based on Levy flight[J]. J4, 2013, 47(4): 638-643.
[3] SON Chang-il , ZHEN Shuai, XIA Shun-ren. Attractor range based affine registration of multi-modal
brain magnetic resonance images
[J]. J4, 2012, 46(9): 1722-1728.
[4] XIE Di, TONG Ruo-feng, TANG Min, FENG Yang. Distinguishable method for video fire detection[J]. J4, 2012, 46(4): 698-704.
[5] Qi lei, JIN Wen-guang, GENG Wei-dong. Human motion capture using wireless inertial sensors[J]. J4, 2012, 46(2): 280-285.
[6] DAI Yuan-ming, WEI Wei, LIN Yi-ning. An improved Mean-shift tracking algorithm based on
color and texture feature
[J]. J4, 2012, 46(2): 212-217.
[7] LIU Chen-bin, PAN Ying, ZHANG Hai-shi, HUANG Feng-ping, XIA Shun-ren. Detecting MGMT expression status of glioma with magnetic
resonance image
[J]. J4, 2012, 46(1): 170-176.
[8] QIAN Cheng, ZHANG San-yuan. Weighted incremental subspace learning algorithm
suitable for object tracking
[J]. J4, 2011, 45(12): 2240-2246.
[9] CAO Ying, HAO Xin, ZHU Xiao-en, XIA Shun-ren. Mammographic mass segmentation algorithm based on
automatic random walks
[J]. J4, 2011, 45(10): 1753-1760.
[10] LV Gu-lai,LI Jian-ping,LI Qiang,YU Li-xing,ZHU Song-ming,LOU Jian-zhong. Method for rootstock position recognition based on machine vision[J]. J4, 2011, 45(10): 1766-1770.
[11] LIU Jian-ming, LU Dong-ming, GE Rong. Global optimization based image inpainting and
its implementation on GPU
[J]. J4, 2011, 45(2): 247-252.
[12] WANG Jin-de, SHOU Li-dan, LI Xiao-yan, CHEN Gang. Bundling features with multiple segmentations for
object-based image retrieval
[J]. J4, 2011, 45(2): 259-266.
[13] ZHAN Jiang-tao, LIU Qiang, CHAI Chun-lei. Facial feature tracking using three-dimensional model and
Gabor wavelet
[J]. J4, 2011, 45(1): 30-36.
[14] LIANG Wen-feng, XIANG Zhi-yu. Algorithm of robust object tracking using PTZ camera[J]. J4, 2011, 45(1): 59-63.
[15] SONG Kun-po, XIA Shun-ren, XU Qing. Algorithm considering correlation of wavelet coefficients for
ultrasound image denoising
[J]. J4, 2010, 44(11): 2203-2208.