改进均值漂移算法的焊缝特征点识别分析

doi:10.12141/j.issn.1000-565X.180656

华南理工大学学报(自然科学版)

改进均值漂移算法的焊缝特征点识别分析

高向东黎扬进刘秀航张艳喜游德勇

广东工业大学广东省焊接工程技术研究中心，广东广州 51000

收稿日期:2019-01-02 出版日期:2019-04-25 发布日期:2019-03-01
通信作者: 高向东(1963-)，男，教授，博士生导师，主要从事焊接自动化、焊接质量控制等研究． E-mail:gaoxd@ gdut.edu.cn
作者简介:高向东(1963-)，男，教授，博士生导师，主要从事焊接自动化、焊接质量控制等研究．
基金资助:
国家自然科学基金资助项目(51675104);广东省教育厅创新团队项目(2017KCXTD010);广东省科技计划项目 (2016A010102015)

Weld Seam Feature Point Recognition Analysis Based on Improved Mean-shift Algorithm

GAO Xiangdong LI Yangjin LIU Xiuhang ZHANG Yanxi YOU Deyong

Guangdong Provincial Welding Engineering Technology Research Center，Guangdong University of Technology， Guangzhou 510006，Guangdong，China

Received:2019-01-02 Online:2019-04-25 Published:2019-03-01
Contact: 高向东(1963-)，男，教授，博士生导师，主要从事焊接自动化、焊接质量控制等研究． E-mail:gaoxd@ gdut.edu.cn
About author:高向东(1963-)，男，教授，博士生导师，主要从事焊接自动化、焊接质量控制等研究．
Supported by:
Supported by the National Natural Science Foundation of China(51675104)，Guangdong Provincial Department of Education Innovation Team Project(2017KCXTD010)and the Science and Technology Planning Project of Guangdong Province， China(2016A010102015)

摘要/Abstract

摘要： 对于线结构光视觉传感的焊缝跟踪系统，快速、精准地识别和提取焊缝特征点是关键．根据结构光条纹线在焊缝处的变形导致的条纹不连续现象，对不锈钢平板对接焊缝和搭接焊缝进行了跟踪试验，提出以改进的均值漂移算法提取焊缝特征点的算法．与传统算法不同，所提算法免去了提取条纹中心线与拟合条纹线过程，直接通过漂移识别焊缝特征点;通过限制漂移算法的搜索方向，防止搜索“回漂”现象;引入漂移加速因子，提高算法执行效率．试验结果表明，利用改进均值漂移算法能够有效地识别焊缝特征点，显著地提高焊缝跟踪的准确度和实时性能．

关键词: 线结构光, 焊缝特征点, 均值漂移, 特征点提取

Abstract: A fast and accurate weld seam feature point recognition is the key of the weld seam tracking system based on structured light sensing． For the streak discontinuity caused by the deformation of structured light stripe line at the weld，tracking tests were carried on butt and lap welds of stainnless steel board，and an improved mean-shift algorithm was proposed to extract the feature point of a weld seam． Unlike the traditional algorithm，the improved algorithm eliminated the process of extracting fringe center line and fitting fringe lineand the feature points of welding seam are identified by drift． In order to prevent from back-shifting，the search direction of the algorithm was limited． To improve the running efficiency，a shifting accelerating factor was introduced． The test shows that the improved mean-shift algorithm can effectively recognize the feature point of a weld seam and saliently improve the accuracy and real-time performance．

Key words: structured light, weld feature point, mean-shift, feature point extraction

中图分类号:

高向东黎扬进刘秀航张艳喜游德勇. 改进均值漂移算法的焊缝特征点识别分析[J]. 华南理工大学学报(自然科学版), doi: 10.12141/j.issn.1000-565X.180656.

GAO Xiangdong LI Yangjin LIU Xiuhang ZHANG Yanxi YOU Deyong. Weld Seam Feature Point Recognition Analysis Based on Improved Mean-shift Algorithm[J]. Journal of South China University of Technology(Natural Science Edition), doi: 10.12141/j.issn.1000-565X.180656.

[1]	王爱丽董宝田武鸿源. 基于多特征概率分布的均值漂移行人跟踪算法[J]. 华南理工大学学报（自然科学版）, 2016, 44(8): 123-130.
[2]	邝泳聪崔亮纯. 基于线纹尺的线结构光视觉传感器标定新方法[J]. 华南理工大学学报（自然科学版）, 2016, 44(1): 71-77.
[3]	元辉李志斌刘微. 基于色度分割与图割算法的视差估计算法[J]. 华南理工大学学报（自然科学版）, 2013, 41(2): 12-18.
[4]	李琦邵春福岳昊. 核窗口尺寸和目标模型自适应的均值漂移跟踪[J]. 华南理工大学学报（自然科学版）, 2013, 41(2): 74-81.
[5]	王年丁业兵唐俊鲍文霞. 带宽自适应的Mean Shift 目标跟踪算法[J]. 华南理工大学学报（自然科学版）, 2011, 39(10): 44-49.
[6]	江焯林黎绍发贾西平祝红丽 . 基于非参数聚类和多尺度图像的目标跟踪[J]. 华南理工大学学报（自然科学版）, 2009, 37(1): 34-41.

改进均值漂移算法的焊缝特征点识别分析

Weld Seam Feature Point Recognition Analysis Based on Improved Mean-shift Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价