基于区域一致性的图割立体匹配

Graph Cut Stereo Matching Based on Region Consistency

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。

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.