|本期目录/Table of Contents|

[1]潘艳华,金 辉,刘金国*,等.基于改进Canny算法的合作靶标边缘检测[J].工业仪表与自动化装置,2023,(05):83-88.[doi:10.19950/j.cnki.cn61-1121/th.2023.05.017]
　PAN Yanhua,JIN Hui,LIU Jinguo*,et al.Cooperative targets edge detection based on improved Canny algorithm[J].Industrial Instrumentation & Automation,2023,(05):83-88.[doi:10.19950/j.cnki.cn61-1121/th.2023.05.017]
点击复制

基于改进Canny算法的合作靶标边缘检测

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2023年05期
页码:
83-88
栏目:
出版日期:
2023-10-15

文章信息/Info

Title:
Cooperative targets edge detection based on improved Canny algorithm
文章编号:
1000-0682（2023）05-0083-06
作者:
潘艳华1; 2; 金 辉1; 刘金国2*; 高 庆2
1.沈阳化工大学 信息工程学院，辽宁 沈阳 110142；
2.中国科学院沈阳自动化研究所 空间自动化技术研究室，辽宁 沈阳 110016
Author(s):
PAN Yanhua1; 2;  JIN Hui1;  LIU Jinguo2*;  GAO Qing2
1.School of Information Engineering, Shenyang University of Chemical Technology, Liaoning Shenyang 110142, China;
2.Space Automation Technology Laboratory, Shenyang Institute of Automation, Chinese Academy of Sciences, Liaoning Shenyang 110016, China
关键词:
合作靶标; 边缘检测; Canny算子; 自适应中值-导向滤波; OTSU算法
Keywords:
cooperative targets;  edge detection;  canny algorithm;  adaptive median filtering-guided filtering;  otsu algorithm
分类号:
TN249
DOI:
10.19950/j.cnki.cn61-1121/th.2023.05.017
文献标志码:
A
摘要:
合作靶标在机器视觉中应用广泛，对合作靶标图像进行采集处理并获取目标的精确定位是目前研究的主流。边缘检测是对靶标图像进行处理的关键一步。该文针对传统Canny算法中存在的缺陷进行了改进，使用自适应中值滤波-导向滤波代替传统高斯滤波，去除噪声的同时保留了边缘信息；计算梯度时增加45°和135°方向，防止边缘细节丢失；采用Otsu算法结合梯度直方图自适应获取阈值，提高阈值的准确性。实验和数据表明，该文算法在边缘完整和细节保留方面更有优势，较传统Canny算法提升约15%～20%。
Abstract:
Cooperative targets are widely used in the field of machine vision, and achieving precise localization of targets is currently a focus of research. Edge detection is a critical step in processing target images. This paper proposes an improved approach to address the limitations of the traditional Canny algorithm.Specifically, this algorithm replaces traditional Gaussian Filter with Adaptive Median Filter and Guided Filter, which effectively suppresses noise while preserving edge information. Additionally, we introduce 45° and 135° directions to gradient calculation to prevent the loss of edge details. Finally we employs the Otsu algorithm in combination with a gradient histogram for adaptive thresholding, which enhances threshold accuracy. Extensive experiments and data analysis demonstrate the superior performance of our approach in terms of edge integrity and detail preservation, which improves by about 15%~20% compared with the traditional Canny algorithm.

参考文献/References:

[1] 何龙,李东,王艳林,等.空间机械臂位姿测量中合作靶标的识别及定位[J].现代电子技术,2018,41(13):106-110, 114.

[2] 金鹏,刘检华,刘少丽,等.基于二维靶标的管路端点位置测量方法[J].计算机集成制造系统,2014,20(11): 2758-2766.
[3] 张刘,张文,王亚明,等.微小卫星交会对接位姿测量中合作目标设计方法[J].液晶与显示,2022,37(3): 415-424.
[4] R Dhivya,R Prakash.RETRACTED ARTICLE:Edge detection of satellite image using fuzzy logic[J].Cluster Computing,2019,22(5):11891-11898.
[5] FU Z,SONG S,WANG X,et al.Imaging the Topology of grounding grids based on wavelet edge detection[J].Ieee Transactions on Magnetics,2018,54(4):1-8.
[6] XIE Saining,TU Zhuowen.Holistically-nested edge detection[J].International Journal of Computer Vision,2017, 125(1): 3-18.
[7] 余小庆,陈仁文,唐杰,等.融合小波变换和新形态学的含噪图像边缘检测[J].计算机科学,2018,45(S2):194-197.
[8] 徐天芝,杨青峰.针对椒盐噪声图像的Canny边缘检测算法[J].计算机时代,2022(9):63-67.
[9] 郝泽兴,郭改枝,代妍玮,等.一种改进Canny算子的边缘检测算法[J].内蒙古大学学报(自然科学版),2022,53(5): 530-537.
[10] 李庆忠,刘洋.基于改进Canny算子的图像弱边缘检测算法[J].计算机应用研究,2020,37(S1):361-363.
[11] ZHANG Xiaog,CHEN Fuen.Lane line edge detection based on improved adaptive Canny algorithm[J].Journal of Physics:Conference Series,2020,1549(2):022131.
[12] YU Weibo,MA Yanhui,ZHENG Liming,et al.Research of improved adaptive median filter algorithm[C]:Springer Berlin Heidelberg,2016: 27-34.
[13] HE Kaiming,SUN Jian,TANG Xiaoou.Guided image filtering[C]:Springer Berlin Heidelberg,2010:1-14.
[14] 梁肇峻,钟俊.基于Otsu算法与直方图分析的自适应Canny算法的改进[J].现代电子技术,2019,42(11): 54-58.
[15] 王洪申,张翔宇,豆永坤,等.图像边缘检测效果的边缘连续性评价算法[J].计算机工程与应用,2018,54(16): 192-196.
[16] 宋人杰,刘超,王保军.一种自适应的Canny边缘检测算法[J].南京邮电大学学报(自然科学版),2018,38(3):72-76.

相似文献/References:

[1]周小军,郭 佳,姜玉泉,等.红外图像几种边缘检测算法对比分析[J].工业仪表与自动化装置,2015,(04):58.
　ZHOU Xiaojun,GUO Jia,JIANG Yuquan,et al.Comparative study on several kinds of edge detection algorithm in infrared image[J].Industrial Instrumentation & Automation,2015,(05):58.
[2]陈宏希.一种基于统计排序滤波的图像边缘检测算法[J].工业仪表与自动化装置,2016,(01):3.
　CHEN Hongxi.An edge detection algorithm based on order-statistic filtering[J].Industrial Instrumentation & Automation,2016,(05):3.
[3]周小军,谭 薇.一种改进Canny算子芯片图像边缘检测方法[J].工业仪表与自动化装置,2022,(04):91.[doi:10.19950/j.cnki.cn61-1121/th.2022.04.018]
　ZHOU Xiaojun,TAN Wei.An improved algorithm for chip image edge detection based on Canny[J].Industrial Instrumentation & Automation,2022,(05):91.[doi:10.19950/j.cnki.cn61-1121/th.2022.04.018]
[4]冯 雨,方成刚,张文东,等.基于机器视觉的碳毡装配检测算法系统设计[J].工业仪表与自动化装置,2024,(02):39.[doi:DOI:10.19950/j.cnki.CN61-1121/TH.2024.02.007]
　FENG Yu,FANG Chenggang,ZHANG Wendong,et al.Design of carbon felt assembly inspection algorithm system based on machine vision[J].Industrial Instrumentation & Automation,2024,(05):39.[doi:DOI:10.19950/j.cnki.CN61-1121/TH.2024.02.007]

备注/Memo

备注/Memo:
收稿日期：2023-06-12

基金项目：
国家自然科学基金项目（51775541）

第一作者：
潘艳华(1998—)，女，山东潍坊人，硕士研究生，主要研究方向为计算机视觉。

通信作者：
刘金国(1978—)，男，博士，研究员，博士生导师，主要研究方向为空间机器人。
更新日期/Last Update: 1900-01-01