基于改进RANSAC的本质矩阵求解方法  

Essence matrix solving method based on improved RANSAC

作　　者：范帅鑫 谷玉海[1] 邹志[2] 崔悦 Fan Shuaixin;Gu Yuhai;Zou Zhi;Cui Yue(Key Laboratory of Modern Measurement and Control Ministry of Education,Beijing Information Science and Technology University,Beijing 100192,China;Changcheng Institute of Metrology&Measurement,Beijing 100095,China)

机构地区：[1]北京信息科技大学现代测控技术教育部重点实验室,北京100192 [2]航空工业北京长城计量测试技术研究所,北京100095

出　　处：《电子测量技术》2024年第7期114-120,共7页Electronic Measurement Technology

基　　金：工业和信息化部民用飞机专项科研技术研究项目(MJ-2018-J-70);北京市科技委促进高校内涵发展-学科建设专项(5112011015);机电测控系统北京市重点实验室开放课题(KF20202223204)项目资助。

摘　　要：针对在单目系统大尺寸测量场景下使用RANSAC算法求解本质矩阵时稳定性和求解精度不高的问题,提出了一种改进RANSAC的本质矩阵求解方法,首先在所有匹配特征点中,通过当前内点求得的本质矩阵对剩余匹配特征点进行重投影误差,并采用相对判别法通过这些误差的值大小来确定当前内点是否为高质量内点,之后在此基础上采用二分法动态调整阈值从若干本质矩阵中寻找最优值。最后,设计了多组视角不同误匹配率下的仿真实验和实际拍摄的实验,实验证明,相较于传统与其他改进的RANSAC算法及LMedS算法,本文改进的算法能够快速确定初始内点并自适应调整阈值,同时求出较好的本质矩阵,满足求解稳定性与精度的要求。Aiming at the problem of low stability and low solution accuracy when using the RANSAC algorithm to solve the essential matrix in the large-scale measurement scene of the monocular system,an improved RANSAC method for solving the essential matrix is proposed.The essential matrix obtained from the points is used to reproject the remaining matching feature points,and use the relative discriminant method to determine whether the current inlier is a high-quality inlier through the value of these errors,and then use the dichotomy method to dynamically adjust the threshold on this basis to find the optimal value from several essential matrices.Finally,this paper designs RANSAC experiments under different mis-matching rates of multiple perspectives.The experiments prove that,compared with traditional and other improved RANSAC algorithms and LMedS algorithms,The improved algorithm in this paper can quickly determine the initial interior points and adaptively adjust the threshold,and at the same time obtain a better essential matrix,which meets the requirements of solution stability and accuracy.

关 键 词：RANSAC 内点 重投影误差 自适应阈值 本质矩阵 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TN209[自动化与计算机技术—计算机科学与技术]