基于改进SURF算法的双目视觉定位  

Binocular Visual Positioning Based on Improved SURF Algorithm

作　　者：韩峰[1] 李晓斌[1] 

机构地区：[1]上海应用技术学院电气与电子工程学院,上海201400

出　　处：《电视技术》2015年第23期22-25,30,共5页Video Engineering

基　　金：上海市地方院校能力建议项目(11510502700);上海市教委科研创新重点计划项目(12ZZ189)

摘　　要：随着机器人技术的发展,机器人视觉也逐渐受到研究人员的重视。在机器人视觉系统的分类中,双目立体视觉系统应用最为广泛。在利用双目立体视觉对物体进行定位时,采用了各方面性能都较突出的SURF算法对摄取的图像特征点进行提取与匹配。由于SURF算法自身的缺陷,在进行特征点匹配时容易产生误匹配现象,为了消除误匹配,文中对SURF算法做了改进,加入了剔除误匹配点的RANSAC算法。实验结果表明,改进后的SURF算法,能够有效提高双目视觉定位的精准度。With the development of robol technology,the research of robot vision get people＇s attention more and more. In robot vision system, the binocular vision applied most widely. When using the binocular vision to locate objects,SURF algorithm is adopted, it has more advantages on performance of many aspects, and it is used to realize feature point extraction and matching of images. Because of the influence of the objective factors, there is false match in the process of SURF matching of feature points. In order to eliminate the false match,the SURF algorithm is improved,the RANSAC algorithm is joined,it can eliminate false match. The experiment results show that the improved SURF algorithm can improve the binocular visual positioning accuracy greatly.

关 键 词：机器人 视觉定位 SURF算法 RANSAC算法 特征点匹配 

分 类 号：TP29[自动化与计算机技术—检测技术与自动化装置]