基于改进ORB特征的视觉里程计算法  

A VISUAL ODOMETRY ALGORITHM BASED ON IMPROVED ORB FEATURE

作　　者：邓宇翔 陈丽 吴泽州 张凯波 Deng Yuxiang;Chen Li;Wu Zezhou;Zhang Kaibo(School of Air Transport,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学航空运输学院,上海201620

出　　处：《计算机应用与软件》2025年第3期233-237,297,共6页Computer Applications and Software

基　　金：国家自然科学基金项目(61733017);机器人国家重点实验室基金项目(2018O13);上海浦江人才计划项目(18PJD018)。

摘　　要：针对视觉里程计算法中特征点提取速度慢和存在冗余的问题,提出一种基于改进ORB特征的视觉里程计算法。设计基于2R准则的特征区域提取策略,减少特征点提取范围,加快算法速率。使用基于对角8点法的FAST算法得到更多的角点,改善FAST角点分布,并采用基于深度的四叉树算法对特征点进行均匀化。进行特征匹配以求解相机位姿。实验结果表明,基于改进ORB特征的视觉里程计算法在相机位姿估计时有更好的精确性和实时性。Aimed at the problems of slow extraction speed and redundancy of feature points in visual odometry algorithm,a visual odometry algorithm based on improved ORB feature is proposed.A feature region extraction strategy based on 2R criterion was designed to reduce the extraction range of feature points and speed up the algorithm.The FAST algorithm based on diagonal 8-point method was used to get more corners and improve the distribution of FAST corners,and the Quadtree algorithm based on depth was used to homogenize the feature points.Feature matching was performed to solve the camera pose.The experimental results show that the visual odometry algorithm based on improved ORB feature has better accuracy and real-time performance in camera pose estimation.

关 键 词：2R准则 特征区域 深度四叉树 视觉里程计 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]