Journal of Software:2000.11(12):1666-1673

Research on Stereo Vision Based Obstacle Detection Algorithm
LI Yan,LIN Xue-yin
Chart / table
Similar Articles
Article :Browse 2716   Download 2567
Received:June 10, 1999    Revised:September 22, 1999
> 中文摘要: 障碍物检测是智能车辆研究中的一个重要内容.用射影几何的方法给出了用重投影变换进行障碍物检测的一般原理,并引入摄像机的内、外参数和姿态参数,建立了重投影变换的参数化模型.为了满足颠簸环境的要求,提出了一种新的基于立体视觉视差分析的障碍物检测算法.实验结果表明,算法具有计算量小和可靠性高的特点.
Abstract:Obstacle detection plays an important role in intelligent vehicle system research. In this paper, the general theory of obstacle detection algorithm is presented based on Ground Plane Transformation. A parametric model for obstacle detection applications is constructed and the influences of the internal, external and pose parameters of the camera on the transformation matrix are discussed. In order to fulfill the requirement in the vibration situations, a new obstacle detection algorithm is proposed based on stereo vision disparity analysis. Experiments show that low computation amount and high reliability can be achieved with the new algorithm.
文章编号:     中图分类号:    文献标志码:
基金项目:国防科技预研项目(JS9603-7) 国防科技预研项目(JS9603-7)
Foundation items:
Reference text:


LI Yan,LIN Xue-yin.Research on Stereo Vision Based Obstacle Detection Algorithm.Journal of Software,2000,11(12):1666-1673