The Study Of Obstacle Detection Technology Based On Binocular Stereovision

With the rapid development of the urbanization and the popularization of the vehicle, traffic problem has increasingly become a hot problem. In recent years, the increment speed of the cars is far more than roads and the establishments of traffic. It leads to so many problems, such as, the traffic accident happened frequently, the personnel casualty grows day by day and the property damage is huge. All these need to develop a new type of cars which can be safe and intelligent. So the concept of intelligence vehicles arises at the historic moment along with it. At the same time, the realization of completely automatic and safe driving intelligent vehicles is a new rapidly developed research area in the recent years.This article mainly aims at automatically obstacle detection in this research area: Automatically detect the obstacles in front of the vehicle by use of the binocular stereovision obstacle detection technology. And introduce one kind of technology which has been called the V- disparity algorithm. It can detect the obstacles which has the surface characteristic, for instance pedestrian, vehicle, wall and so on. Moreover, this algorithm is insensitive to illumination, shadow and so on. It is suitable to detect obstacles under the complex background of the city.Specifically speaking, this article mainly includes three partial contents: First, We reduce the influence of the complex background by detecting the path scribe mark and separating the path surface with the complex redundant background.Then, we seek the homologues from the binocular images fast and accurately by stereo matching. And get high-quality stereo disparity map of the images. It then will be the basis of the obstacle detection.Finally, further builds the V- disparity map according to the stereo disparity map, extracts the straight line information in the V- disparity map, and through these straight line information can get the approximate region of the target. Then we can detect the obstacles. The obstacles include static and movement objects.