基于SURF算法的双目视觉特征点定位研究  

Research on Binocular Visual Feature Points Positioning Based on Improved SURF Matching Algorithm

作　　者：王永锋 石超 徐子锋 陈龙[1] WANG Yongfeng;SHI Chao;XU Zifeng;CHENG Long(College of Mechanical Engineering ,University of Shanghai for Science and Technology ,Shanghai 200093,China)

机构地区：[1]上海理工大学机械工程学院,上海200093

出　　处：《软件工程》2019年第3期5-8,共4页Software Engineering

摘　　要：针对双目视觉立体图像特征点匹配质量不好导致定位精度低的问题,本文提出改进SURF匹配的特征点定位方法。在改进的SURF匹配算法中,采用双向匹配、NNDR约束、对称性约束、极线约束和交叉匹配约束的方法,提高了图像特征点匹配的质量。在双目视觉特征点定位中,采用公垂线段中点法具有更高的特征点定位精度。实验证明,该算法的特征点定位精度更高,同时可以达到实时三维重建效率。Aiming at the problem of low positioning accuracy caused by poor matching quality of binocular stereo image feature points,this paper proposes a feature point 3D reconstruction method based on improved SURF matching algorithm.In the improved SURF matching algorithm,two-way matching,NNDR constraint,symmetry constraint,polar line constraint and cross matching constraint are used to improve the quality of image feature point matching.In binocular vision feature point positioning,the common vertical midpoint method has higher feature point positioning accuracy.Experimental results show that the proposed algorithm has higher accuracy of feature point positioning and can achieve real-time 3D reconstruction efficiency.

关 键 词：特征点重建 SURF算法 双目视觉 最小二乘法 公垂线段中点法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]