基于ELAS立体匹配算法的研究与改进

摘要

在双目机器人视觉伺服控制中,双目立体匹配算法的实时性和准确性,对机器人的精确定位及控制至关重要.在研究现有的一些先进性立体匹配算法的基础上,引入一种基于视差平面的局部立体匹配算法ELAS(算法,将该算法与先进的立体匹配算法对比发现,其克服了现有算法需要给定最大视差值范围才能获得较好视差图的缺点,综合处理时间和处理效果,表现最好.介绍ELAS算法原理,并分析其存在的问题,针对ELAS算法处理效果不佳的问题,根据视差连续原理,研究改进的ELAS算法,并使用引导滤波器处理视差图.实验证明,改进的ELAS算法显著提高了原算法的效果,而处理时间增加不多,在不考虑实时性的情况下,结合上述滤波器后,处理效果能够接近真实视差图.%Binocular stereo matching algorithm is real-time and accurate in the binocular vision servo control system,which is very important for the accurate positioning and control of the robot.Based on the study of some advanced stereo matching algorithms,this paper introduces an algorithm of local stereo matching based on parallax plane-ELAS (Efficient LArge-scale Stereo) algorithm,introduces the principle of ELAS algorithm,Which overcomes the shortcomings of these existing algorithms in which the best disparity map cannot be obtained until the maximum disparity value range is given.The best performance is obtained by considering the combination of the processing time and processing effect.Aiming at the problem that the ELAS algorithm does not work well, the improved ELAS algorithm is studied based on the principle of disparity continuity.The disparity map is processed using the guided filter.Experiments show that the improved ELAS algorithm improves the performance of the original algorithm significantly.Without considering the real-time performance, combined with the above-mentioned filters, the processing effect can be close to the real disparity map, which is of great significance in 3D reconstruction and visual servoing.