登录 | 注册 | 退出 | 公司首页 | 繁体中文 | 满意度调查
综合馆
Hopfield网络在视差空间上的立体匹配求解
  • 摘要

    由于边界区域的匹配精度是立体匹配问题的瓶颈,这里采用一种基于特征的匹配算法来重点研究场景中边界区域的匹配.首先针对立体匹配问题,提出一种基于RBF的边界提取算法,使得边界区域成为待匹配的像素点.研究像素点匹配需要满足的约束,构建相应的能量方程,接着采用Hopfield网络对能量函数进行优化来获得问题的求解.由于针对的是整个边界区域,直接将特征点输入网络会导致神经元数目过多、复杂度过高.为了降低算法复杂度,提出从视差空间上来构造网络模型.最后通过大量实验来验证算法的性能,包括标准图片、噪声图片与真实的场景图片.实验证明新算法能大大提高边界区域精度,克服了立体匹配的瓶颈,明显提高了整体区域精度,算法有很强的鲁棒性和实用性,即使在复杂情况下也能取得较好的效果.

  • 作者

    徐昇  业宁  朱发  徐姗姗  周溜溜  Xu Sheng  Ye Ning  Zhu Fa  Xu Shanshan  Zhou Liuliu 

  • 作者单位

    南京林业大学信息科学与技术学院 南京 210037

  • 刊期

    2013年5期 ISTIC EI PKU

  • 关键词

    立体匹配  边界特征提取  能量函数  Hopfield神经网络  视差空间 

参考文献
  • [1] 徐昇 ,云挺,业宁. 最短路径模型下的双目立体匹配算法研究. 计算机科学与探索, 2011,4
  • [2] Szeliski R.;Scharstein D.. Sampling the disparity space image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,3
  • [3] Kuk-Jin Yoon;In So Kweon. Adaptive support-weight approach for correspondence search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,4
  • [4] Karim Achour;Lyes Mahiddine. Hopfield Neural Network Based Stereo Matching Algorithm. Journal of mathematical imaging and vision, 2002,1
  • [5] Prazdny K. A disparity gradient limit for binocular fusion. Science, 1980,4444
  • [6] Bleyer M. A layered stereo algorithm using image segmentation and global visibility constraints. Piscataway,NJ:IEEE, 2004
  • [7] Trinh H;McAllester D. Unsupervised learning of stereo vision with monocular cues. London:British Machine Vision Association, 2009
  • [8] Sun J;Li Y;Kang S B. Symmetric stereo matching for occlusion handling. Piscataway,NJ:IEEE, 2005
  • [9] Mukherjee D;Wang G;Wu J. Stereo matching algorithm based on curvelet decomposition and modified support weights. Piscataway,NJ:IEEE, 2010
  • [10] Einecke N;Eggert J. A two-stage correlation method for stereoscopic depth estimation. Piscataway,NJ:IEEE, 2010
  • [11] Forstmann S;Kanou Y;Thuering S. Real-time stereo by using dynamic programming. Piscataway,NJ:IEEE, 2004
  • [12] Boykov Y;Veksler O. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,11
  • [13] Sun J;Zheng N N;Shum H Y. Stereo matching using belief propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,07
  • [14] Jung H Y;Lee K M;Lee S U. Stereo matching using scanline disparity discontinuity optimization. Beilin:Springer-Verlag, 2006
  • [15] Ogale A S;Aloimonos Y. Shape and the stereo correspondence problem. International Journal of Computer Vision, 2005,12
  • [16] Mattoccia S. A locally global approach to stereo correspondence. Piscataway,NJ:IEEE, 2009
  • [17] Wan G;Wang A;Li S. Solving stereo correspondence through minimizing energy function with higher-order cliques. Piscataway,NJ:IEEE, 2008
查看更多︾
相似文献 查看更多>>
3.227.252.54