Study Of The Binocular Vision System Based On Line And Plane Features

The main goal of computer stereo vision is to restore the depth information of an object from two-dimensional images. Generally, we would like to restore the depth information by using of only those images that captured from two different view points. The fundamental principle of Computer stereo Vision with dual-camera, that is, the binocular vision, has a strong resemblance to the visual perception procedure of humankind. Getting different images via two different view points and then calculating the position deviation of image pixels based on triangular measure, and then, the depth information of the object that we interested can be attained.We consider the Traffic Video Detection System as our research background. A brief overview of the state of the art about stereo vision researches is presented first. Then, the algorithms we developed for binocular vision are presented, including the stereo matching algorithm based on linear features, the coplanarity determination algorithm of line segments, and the merging algorithm of planes. Finally, the design and realization of our binocular vision system is given.Our work contributes in the following aspects:1) The algorithms about stereo matching based on line features are proposed. The algorithms are, the line segments matching algorithm and the end-points matching algorithm of line segments. When the results of the stereo matching are obtained, then we can get depth information of the line segments.2) The coplanarity judgement procedure of line segments is developed. Based on the information obtained in 1), we provide the coplanarity judgement algorithm of line segments as well as the merging algorithm of planes.3) The system of our binocular vision is designed and implemented. And some experiments are also conducted about the system. The experimental results show that the algorithms we proposed are efficient.