[1]王建卫.基于圆环模板和标志矩阵的角点检测算法[J].计算机技术与发展,2019,29(06):66-70.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 014]
　WANG Jian-wei.A Corner Detection Algorithm Based on Ring Template and Mark Matrix[J].,2019,29(06):66-70.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 014]
点击复制

基于圆环模板和标志矩阵的角点检测算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年06期
页码:
66-70
栏目:
智能、算法、系统工程
出版日期:
2019-06-10

文章信息/Info

Title:
A Corner Detection Algorithm Based on Ring Template and Mark Matrix
文章编号:
1673-629X(2019)06-0066-05
作者:
王建卫
东北林业大学 机电工程学院,黑龙江 哈尔滨 150040
Author(s):
WANG Jian-wei
School of Mechanical and Electrical Engineering,Northeast Forest University,Harbin 150040,China
关键词:
角点检测; 圆形模板; 角点标志矩阵; 四叉树; 行程编码
Keywords:
corner detection; circular template; corner mark matrix; quadtree; run length coding
分类号:
TP391.41
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 06. 014
摘要:
为了解决计算机视觉系统中图像边缘检测时边缘点和边缘段同时检出的问题,提出了一种基于圆环模板和角点标志矩阵表示的角点检测算法。 首先通过设置较小的阈值,应用圆环模板提取较多的灰度图像的亮度变化点作为候选角点;记录角点在原图像中的位置,并将原图像中该像素值设置为1,其他像素设置为0,建立角点标志矩阵,并将矩阵按照四叉树结构分解;统计子矩阵的1的个数和所占比例,将个数和比例较低的子块的角点标记删除;对其他的子矩阵分别采用行方式和列方式进行行程编码,在编码中对连续的1序列仅留第一个,将后续的1置为0。 记录同时在行方式和列方式结果矩阵中的1 元素为角点。 实验结果表明,与 Moravec 算法、Harris 算法与 FAST 算法相比,该算法具有角点检测准确和适用面广的优点,在一定程度上解决了减少角点数目的问题。
Abstract:
In order to solve the problem of simultaneous detection of edge points and edge line segments during the edge detection in computer vision system,we propose a corner detection algorithm on basis of the ring template and the corner mark matrix. At first the smaller threshold is set up. More pixels with the brightness change extracting by the ring template are treated as the candidate corner pixels. The corner locations are recorded in the original age,and the pixel value of the original image is set to 1,and the other pixels are set to 0. The corner marker matrix is established and decomposed according to the quadtree structure. The number and proportion of the 1 are calculated in the submatrices. And the corners in the subblocks are deleted from the corner marks with the lower numbers and the lower proportions. The sub matrices are coded in line and column respectively through run length coding. The first 1 element in the consecutive coding sequences is kept,and the subsequent 1 is set to 0. The 1 element in the result matrix of the row and column mode are recorded as the corner points at the same time. The experiment shows that compared with Moravec algorithm,Harris algorithm and FAST algorithm,the proposed algorithm has the advantages of the accurate corner detection and the wide application,which solves the problem of reducing the number of corner points to a certain extent.

相似文献/References:

[1]蔡丽欢 廖英豪 郭东辉.图像拼接方法及其关键技术研究[J].计算机技术与发展,2008,(03):1.
　CAI Li-huan,LIAO Ying-hao,GUO Dong-hui.Study on Image Stitching Methods and Its Key Technologies[J].,2008,(06):1.
[2]卢瑜 郝兴文 王永俊.Moravec和Harris角点检测方法比较研究[J].计算机技术与发展,2011,(06):95.
　LU Yu,HAO Xing-wen,WANG Yong-jun.Research on Moravec and Harris Corner Algorithm[J].,2011,(06):95.
[3]昌海亮,席 隆.改进的棋盘格自生长亚像素角点检测算法[J].计算机技术与发展,2022,32(S1):40.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 009]
　CHANG Hai-liang,XI Long.An Improved Checkerboard Self-growing Subpixel Corner Detection Algorithm[J].,2022,32(06):40.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 009]

更新日期/Last Update: 2019-06-10