机器视觉中角点检测算法研究  

Research on Corner Detection Algorithms in Machine Vision

作　　者：尚硕 曹建荣[1] 汪明[1] 郑学汉[1] 高鹤[1,2] SHANG Shuo;CAO Jianrong;WANG Ming;ZHENG Xuehan;GAO He(School of Information and Electrical Engineering,Shandong Jianzhu University,Jinan 25010l,China;Shandong Zhengchen Technology Co.,Ltd.,Jinan 25010l,China)

机构地区：[1]山东建筑大学信息与电气工程学院,济南250101 [2]山东正晨科技股份有限公司,济南250101

出　　处：《计算机测量与控制》2024年第1期217-225,共9页Computer Measurement &Control

基　　金：国家自然科学基金(62073196,U1806204)。

摘　　要：角点检测是运动检测、图像匹配、视频跟踪、三维重建和目标识别等必不可少的关键步骤,角点检测的准确性直接影响实验结果;为了更好地了解角点检测技术的发展现状,根据3种现有的角点检测方法分类对角点检测方法及相关改进进行了总结分析,并选择了FAST、SUSAN、SIFT、Shi-Tomas这几种较为典型的角点检测算法进行了实验对比,并给出了实验结果;不同的实际应用对角点检测的要求不同,不同的角点检测算法也可以相互结合,通过对现有角点检测技术的总结分析为在实际应用中对角点检测技术的选择和改进方向提供了借鉴和参考。Corner detection is a key step for motion detection,image matching,video tracking,3D reconstruction,and target recognition.The precision of corner detection directly influences on experimental results.In order to better comprehend the development status of corner detection technologies,the corner detection methods and associated enhancements are summarized and analyzed based on three types of existing corner detection algorithms.The typical detection algorithms of features from the accelerated segment test(FAST),small unit-value segment assimilating nucleus(SUSAN),scale-invariant feature transform(SIFT),and Shi-Tomas are chosen to conduct the experimental comparison,and the results of the experiment are provided.Different practical applications have different requirements for corner detection,and various corner detection algorithms can also be combined with each other.Through a summary and analysis of the existing corner detection technologies,this paper provides a reference for the selection and development of corner detection technologies in practical applications.

关 键 词：角点检测 运动检测 图像匹配 视频跟踪 三维重建 目标识别 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]