首页 > 论文 > 中国激光 > 41卷 > 8期(pp:812001--1)

基于颜色内相关和自适应支撑权重的立体匹配算法

Stereo Matching Algorithm Based on the Inter Color Correlation and Adaptive Support Weight

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

立体匹配的关键问题是确定一个合适的匹配代价关系,颜色内相关作为像素点的固有特性,能够有效地反映出匹配像素点间的微小差异。对传统的自适应支撑权重 (ASW)方法进行改进,提出了一种基于颜色内相关和自适应支撑窗口的立体匹配算法,该方法结合了颜色相似性、欧式距离相似性和颜色内相关相似性来确定匹配窗口内像素点的权重大小。同时为了消除光照不同对图像匹配结果的影响,将匹配点先进行rank变换后再进行匹配代价关系计算。对计算出的初始视差图进行三步优化,剔除由图像遮挡、重复等引起的不同视差错误,从而得到最终的视差结果。通过在Matlab软件平台上对国际标准图像进行测试,实验结果表明该方法得到的视差结果的平均错误率低,且明显优于其他局部匹配方法,具有很强的稳健性和较低的误匹配率。

Abstract

It is crucial to choose a suitable matching cost relationship for area-based stereo matching. Inter color correlation as the inherent characteristics of pixel, can effectively show the small matching differences between pixel. The traditional method of adaptive support weight is improved, and a new matching algorithm that combines the color similarity, Euclidean distance similarity and inter color correlation similarity is proposed to compute the corresponding support weight. Meanwhile, in order to solve the brightness difference between the stereo image pairs, matching pixel are transformed by rank and calculating the matching cost relationship. Various errors in the disparity results are effectively handled in a three-step refinement process. The experimental results based on Matlab show that its performance is the best among local matching methods, and its robustness is very strong, as well as low false match rate.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN29

DOI:10.3788/cjl201441.0812001

所属栏目:自适应光学

基金项目:国家自然科学基金(61101119)、江苏省普通高校研究生科研创新基金(CXZZ120183)、江苏省自然科学基金(BK2011699)

收稿日期:2014-02-24

修改稿日期:2014-04-10

网络出版日期:--

作者单位    点击查看

龚文彪:南京理工大学江苏省光谱成像与智能感知重点实验室, 江苏 南京 210094
顾国华:南京理工大学江苏省光谱成像与智能感知重点实验室, 江苏 南京 210094
钱惟贤:南京理工大学江苏省光谱成像与智能感知重点实验室, 江苏 南京 210094
任建乐:南京理工大学江苏省光谱成像与智能感知重点实验室, 江苏 南京 210094

联系人作者:龚文彪(gongwenbiao2011@163.com)

备注:龚文彪(1990—),男,硕士研究生,主要从事图像处理、立体匹配等方面的研究。

【1】Gu Cheng, Qian Weixian, Chen Qian, et al.. Rapid head dectection method based on binocular stereo vision[J]. Chinese J Lasers, 2013, 41(1): 0108001.
顾骋, 钱惟贤, 陈钱, 等. 基于双目立体视觉的快速人头检测方法[J]. 中国激光, 2013, 41(1): 0108001.

【2】Zhang K, Lu J, Lafruit G. Cross-based local stereo matching using orthogonal integral images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19(7): 1073-1079.

【3】Veksler O. Fast variable window for stereo correspondence using integral images[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognitions, 2003, 1: I-556-I-561.

【4】Yoon K J, Kweon I S. Adaptive support-weight approach for correspondence search[J]. IEEE Trans Pattern Anal Mach Intell, 2006, 28(4): 650-656.

【5】Hou Junjie, Wei Xinguo, Sun Junhua. Calibration method for binocular vision based on matching synthetic images of concentric circles[J]. Acta Optica Sinica, 2012, 32(3): 0315003.
候俊捷, 魏新国, 孙军华. 基于同心圆合成图像匹配的双目视觉标定[J]. 光学学报, 2012, 32(3): 0315003.

【6】Yang Q, Wang L, Yang R, et al.. Stereo matching with color-weighted correlation, hierarchical belief propagation, and occlusion handling[J]. IEEE Transactions on Pootem Analysis and Mechine Intelligence, 2009, 31(3): 492-504.

【7】Klaus A, Sormann M, Karner K. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure[J]. Proceedings of the IEEE 18th International Conference on Pattern Recognition, 2006, 3: 15-18.

【8】Hu W, Zhagn K, Sun L, et al.. Virtual support window for adaptive-weight stereo matching[C]. Proceedings of the IEEE Visual Communications and Image Processing, 2011. 1-4.

【9】De-Maeztu L, Villanueva A, Cabeza R. Stereo matching using gradient similarity andlocally adaptive support-weight[J]. Pattern Recogn Lett, 2011, 32(13): 1643-1651.

【10】Lei C, Selzer J, Yang Y. Region-tree based stereo using dynamic programming optimization[J]. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognitim, 2006, 2: 2378-2385.

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF