中国科学院自动化研究所机构知识库

Monocular vision system is very commonly used in robots. But it is difficult for a monocular vision system to obtain the depth information of object, which results in the failure of 3D (three dimensional) measurement. In this paper, a motion-based measurement method is proposed for a monocular vision system consisting of yawing camera. The depth of object is estimated with the motion increment based on the interaction matrix when the camera translates with the moving platform. Then the object's X- and Y- coordinates are computed with the depth and its imaging coordinates. In the two typical cases of front view and side view, the errors caused by different variables are analyzed. The error in the motion increment is always an important error source. The experimental results verify the effectiveness of the proposed measurement method.