基于直线先验知识的工件缝隙水平集分割方法

doi:10.3969/j.issn.1006-2475.2016.01.016

计算机与现代化

基于直线先验知识的工件缝隙水平集分割方法

1.同济大学电子与信息工程学院计算机科学与技术系, 上海201804； 
2.同济大学电子与信息工程学院CAD研究中心, 上海201804

收稿日期:2015-08-20 出版日期:2016-01-22 发布日期:2016-01-26
作者简介:陈启明(1990-),男,浙江绍兴人,同济大学电子与信息工程学院计算机科学与技术系硕士研究生,研究方向:计算机视觉; 王志成(1975-),男,上海人,副研究员,博士,研究方向:仿真与多媒体。

Weld Seam Level Set Segmentation Method Based on Straight Line Prior Knowledge

1. Department of Computer Science and Technology, College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China；
2. CAD Center, College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China

Received:2015-08-20 Online:2016-01-22 Published:2016-01-26

摘要/Abstract

摘要： 焊缝识别和分割是实现自动化焊接的重要环节。点焊过程产生的焊疤及药皮燃烧产生的喷射物，会在分割图像中产生严重噪声，从而影响焊缝分割的效果。考虑到实际应用中焊缝呈现直条型，本文提出一种基于直线先验形状信息的水平集分割方法，将缝隙的曲率变化作为先验信息正则化主动轮廓模型，过滤掉伪焊缝，提高了算法的鲁棒性。与传统的CV模型和改进的LBF模型相比，本文所提方法具有更好的分割效果和更高的准确率。


关键词: 焊缝分割, 水平集, 先验知识

Abstract: Weld seam identification and segmentation is an important part of automated welding. The burr produced during spot welding process will bring serious noise in the image, thus affecting the weld segmentation results. Taking the shape of weld seam into account, the paper proposed a weld seam level set segmentation method based on straight line prior information. Since the weld seam is always a straight bar, the proposed method takes the curvature of weld seam as a prior information regularization term, and added it to the active contour models. This is very useful to filter out pseudo-seam, thus it improves the robustness of the algorithm. Compared with the traditional CV model and the improved LBF model, the proposed method is of better segmentation results and higher accuracy.


Key words: weld seam segmentation, level set, prior knowledge

中图分类号:

TP391

陈启明1，2，王志成1,2. 基于直线先验知识的工件缝隙水平集分割方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2016.01.016.

CHEN Qi-ming1,2, WANG Zhi-cheng1,2. Weld Seam Level Set Segmentation Method Based on Straight Line Prior Knowledge[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2016.01.016.

参考文献

［1］赵相宾,李亮玉,夏长亮,等. 激光视觉焊缝跟踪系统图像处理［J］. 焊接学报, 2007,27(12):42-44.
［2］孔萌,马超,林涛,等. 基于被动视觉的弧焊机器人自主焊缝轨迹获取与跟踪方法［C］// 第七届中国机器人焊接学术与技术交流会议. 2008:48-51.
［3］谢静,杨晓燕,徐长航,等. 基于形态学方法的工件表面缺陷红外热像检测技术［J］. 中国石油大学学报(自然科学版), 2012,36(3):146-150.
［4］李爱莲,杨芮. 基于蛇模型的指针式表盘的分割研究［J］. 科学技术与工程, 2014,14(3):208-211.
［5］杨利萍,邹琪. 基于先验形状信息的水平集图像分割［J］. 计算机科学, 2012,39(8):288-291.
［6］薛维琴,周志勇,郑健,等. 含先验形状的水平集血管分割方法［J］. 计算机辅助设计与图形学学报, 2013,25(8):1213-1222.
［7］ Burger M, Osher S. A survey on level set methods for inverse problems and optimal design［J］. European Journal of Applied Mathematics, 2005,16(2):263-301.
［8］ Osher S, Shu C W. High-order essentiall non-oscillatory sechemes for Hamilton-Jacobi equation［J］. SIAM Journal of Numerical Analsis, 1991,28(4):907-922.
［9］ Osher S, Fedkiw R. Level Set Methods and Dynamic Implicit Surfaces［M］. New York: Springer, 2002:22-114.
［10］Zhao Hong-kai, Chan T, Merriman B, et al.A variational level set approach to multiphase motion［J］. Journal of Computational Physics, 1996,127:179-195.
［11］Lie J, Lysaker M, Tai Xuecheng. A variant of the Level set method and application to image segmentation［J］. Mathematics of Computation, 2006,75(255):1155-1174.
［12］Smith K A, Solis F J, Chopp D L. A projection method for motion of triple junctions by level sets［J］. Interfaces and Free Boundaries, 2002,4(3):263-276.
［13］Mumford D, Shah J. Optimal approximations by piecewise smooth functions and associated variational problems［J］. Communications on Pure and Applied Mathematics, 1989,42(5):577-685.
［14］Chan T, Vese L. An active contour model without edges［M］// 〖JP2〗Scale-Space Theories in Computer Vision. Springer, Berlin Heidelberg. 1999:141-151.
［15］Li Chunming, Huang Rui, Ding Zhaohui, et al. A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI［J］. IEEE Transactions on Image Processing, 2011,20(7):2007-2016.
［16］Li Chunming, Xu Chengyang, Gui Changfeng, et al. Distance regularized level set evolution and its application to image segmentation［J］. IEEE Transactions on Image Processing, 2010,19(12):3243-3254.
［17］崔玉玲. 基于改进符号距离函数的变分水平集图像分割算法［J］. 模式识别与人工智能, 2013,26(11):1033-1040.

[1]	王威，李志华，吴世宇. 基于多特征融合的车辆阴影检测与去除[J]. 计算机与现代化, 2019, 0(12): 49-.
[2]	金凯成,王翊,郑申海,欧阳自鹏. 基于三维感兴趣区域和模糊聚类的肝脏肿瘤分割[J]. 计算机与现代化, 2015, 0(8): 8-12.
[3]	蒲新华;李永久. 基于CV模型的目标检测与提取[J]. 计算机与现代化, 2013, 1(11): 25-27.
[4]	于若飞. 背景提取和水平集相结合的运动目标轮廓提取方法[J]. 计算机与现代化, 2011, 7(7): 40-44.
[5]	张裕徐刚何鹏刘丽琼. 水平集方法的改进及在医学图像上的应用 [J]. 计算机与现代化, 2010, 1(12): 59-60.

基于直线先验知识的工件缝隙水平集分割方法

Weld Seam Level Set Segmentation Method Based on Straight Line Prior Knowledge

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价