一种快速自适应的Harris角点检测方法研究  

Study of Fast Adaptive Harris Corner Detection Method

作　　者：王慧勇[1,2] 

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240 [2]上海电视广播集团,上海200070

出　　处：《电视技术》2013年第19期208-212,共5页Video Engineering

基　　金：国家"863"计划项目(2011AA01A107);国家科技支撑项目(2013BAH54F04);上海市科委科研项目(10dz2253200)

摘　　要：Harris角点检测算法在图像处理中使用非常广泛,有着较高检测率,但算法运算量比较大,实时性不高。同时,该算法无法设置通用阈值处理不同图像。针对这些问题,提出一种快速自适应Harris角点检测算法。该算法先使用Fast算法,对图像进行预筛选,再使用Harris算法,并构造自适应阈值。实验结果表明,该算法可以有效克服阈值选择不当造成的角点冗余或丢失,并可大幅减少运算量。Harris corner detection algorithm is widely used in image processing.It has a high detection rate,but it needs much time to calculate.At the same time,the algorithm cannot set the universal threshold.To solve these problems,a fast adaptive corner detection algorithm is proposed based on the Harris.The algorithm uses Fast algorithms for image pre-screening,and then uses the Harris algorithm with the constructed adaptive threshold.Experimental results show that the algorithm can effectively overcome corner redundant or missing caused by the improper setting threshold,and improve efficiency.

关 键 词：角点检测 HARRIS算法 自适应阈值 Fast算法 

分 类 号：TN911.73[电子电信—通信与信息系统]