基于U-V视差算法的障碍物识别技术研究

Research of Obstacle Recognition Technology Based on U-V Disparity

介绍了U-V视差算法的数学模型和实现方法,给出了相应的实验结果.通过改进传统的U-V视差算法,引入直线拟合和聚类算法,使检测障碍物效率得到了很大的提高.实验表明改进后的U-V视差算法检测障碍物速度快、精度高,同时适合凹凸障碍物检测,是种较好的检测算法.

The algorithm of mathematical model and algorithm implementation of U-V disparity is introduced and the results of the experiments were presnted. Liner fitting and clustering were introduced to improve the traditional U-V Disparity and efficiency of obstacle detection was improved greatly. U-V Disparity is an excellent algorithm according to experiments, by which obstacles can be detected rapidly and accurately, and U-V Disparity can be used to detect both negative and positive obstacles.