摘要： 为了搜寻移动机器人周围最大的可通行区域，采用全向立体视觉系统，提出获取可靠的致密三维深度图方法。视觉系统由1个普通相机和2个双曲面镜组成。当系统标定后，空间点的三维坐标可以通过匹配上下镜面的成像点计算得出。匹配方法分3步：最大FX匹配，特征匹配和歧义去除。定义合适的能量函数通过动态规划来实现剩余点的匹配。实验表明该系统精度高、具有实用价值。

关键词: 全向立体视觉, 图像匹配, 动态规划, 深度图

Abstract: This paper deals with the problem of finding the largest passable areas around a mobile robot. It proposes a method to obtain reliable dense 3D depth maps using a novel omnidirectional stereo vision system. The vision system is composed of a perspective camera and two hyperbolic mirrors. Once the system has been calibrated and two image points respectively projected by upper and below mirrors are matched, the 3D coordinate of the space point can be acquired by means of triangulation. To achieve the largest reliable dense matching, the method is divided into three steps: reliable FX-dominant matching, feature matching and ambiguous removal. The remaining points between features are matched using dynamic programming with modified energy functions adapted well to the system. Experiments show that the vision system is feasible as a practical stereo sensor for accurate 3D map generation.

Key words: omnidirectional stereo vision, image matching, dynamic programming, depth map

中图分类号: 

• TP391