论文:2017,Vol:35,Issue(1):160-163
引用本文:
曹国震, 彭寒. 基于区域一致性的图割立体匹配[J]. 西北工业大学学报
Cao Guozhen, Peng Han. Graph Cut Stereo Matching Based on Region Consistency[J]. Northwestern polytechnical university

基于区域一致性的图割立体匹配
曹国震1, 彭寒2
1. 西安航空学院, 陕西 西安 710077;
2. 西北工业大学 计算机学院, 陕西 西安 710072
摘要:
面向深度信息获取的立体匹配由于其处理快速、操作简单和隐蔽性好等一系列优点已应用于机器人视觉导航、医学成像和军事等领域,已成为立体视觉中的一个热点方向。由于图割算法不仅精度高,收敛速度快,并且对于光照变化、弱纹理等区域的匹配效果也比其他算法好。但是图割算法没有考虑图像的全局一致性,针对其不足之处,文章提出了基于区域一致性约束的图割立体匹配算法,并通过matlab仿真验证了算法有效性。
关键词:    立体匹配    图割    一致性    matlab   
Graph Cut Stereo Matching Based on Region Consistency
Cao Guozhen1, Peng Han2
1. Xi'an Institute of Aeronautical Engineering, Xi'an 710077, China;
2. School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
for obtaining the depth information of stereo matching because of its fast, simple operation and good concealment and a series of advantages has been applied in robot navigation, medical imaging and military fields, has become a hotspot in stereo vision. Because the graph cut algorithm not only has high precision, fast convergence speed, but also has better matching effect than other algorithms in the area of illumination change, weak texture and so on. But the graph cut algorithm does not consider the global consistency of the image, for its shortcomings, this paper puts forward the regional consistency constraint of stereo matching algorithm based on graph cuts, and the effectiveness is proved by MATLAB simulation.
Key words:    stereo matching    graph cut    consistency    MATLAB   
收稿日期: 2016-09-02     修回日期:
DOI:
基金项目: 陕西省科技工业攻关项目(2016GY-139)与陕西省自然科学基金(2016NM1014)资助
通讯作者:     Email:
作者简介: 曹国震(1980-),西安航空学院讲师,主要从事计算机应用技术及图像处理研究。
相关功能
PDF(1500KB) Free
打印本文
把本文推荐给朋友
作者相关文章
曹国震  在本刊中的所有文章
彭寒  在本刊中的所有文章

参考文献:
[1] Geiger D and Girosi F. Parallel and Deterministic Algorithms for MRFs:Surface Reconstruction[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991, 13(5):401-412
[2] Boykov Y, Veksler O, Zabih R. Fast Approximate Energy Minimization via Graph Cuts[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2001, 23(11):1222-1239
[3] Sun J, Zheng N, Shum H. Stereo Matching Using Belief Propagation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(7):787-800
[4] Bobick Intille. Large Occlusion Stereo[J]. International Journal of Computer Vision, 1999, 33(3):181-200
[5] 郑志刚, 汪增福. 基于区域间协同优化的立体匹配算法[J]. 自动化学报, 2009, 35(5)469-477 Zheng Zhigang, Wang Zengfu. Stereo Matching Algorithm Based on Collaborative Optimization between Regions[J]. Automation Journal, 2009, 35(5):469-477(in Chinese)
[6] Scharstein Szeliski. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms[J]. International Journal of Computer Vision, 2002, 47(1):7-42
[7] Kolmogorov Zabih. Computing Visual Correspondence with Occlusions Using Graph Cuts[C]//Proceedings of International Conference on Computer Vision, 2001
[8] Kolmogorov Zabih. Multi-Camera Scene Reconstruction via Graph Cuts[C]//Proceedings of European Conference on Computer Vision, 2002