SIA OpenIR  > 光电信息技术研究室
Alternative TitleMethods Research of Plane Parts Recognition and Localization Based on Regional Division
唐宇; 吴清潇; 朱枫
Source Publication机械设计与制造
Contribution Rank1
Keyword工件分拣 形状特征 目标识别 模板匹配 工件定位
Abstract视觉技术在工业生产中得到了越来越广泛的应用,对提高生产效率,达到生产智能化的目的起着至关重要的作用。以工业机器人实现工件分拣为背景,提出一种基于区域划分的平面工件识别与定位方法,该方法先利用LSD(Line Segment Detector)进行直线段的提取,然后将干扰的杂线段分类进行剔除,在保留的轮廓线段基础上进行直线段的连接和区域划分,最后利用各个区域的形状特征向量和模板的形状特征向量进行比对,以完成工件的识别和定位。实验结果表明,提出的算法能有效的识别和定位工件。
Other AbstractVision technology has been widely applied in industry,playing a vital role in improving production efficiency and achieving the purpose of the production of intelligence. For parts sorting of industrial production process,it proposed an algorithm of positioning and recognition of plane parts based on shape feature. Firstly,the algorithm used LSD to extract line segments,and then removed miscellaneous line segments; then processed the retaining outline to complete regional division; last based on the result of regional division,shape feature vector of each region was compared with the shape feature vector of template to complete the recognition and positioning of the parts. Experimental results show that the proposed algorithm can effectively identify and locate parts.
Document Type期刊论文
Recommended Citation
GB/T 7714
唐宇,吴清潇,朱枫. 平面工件的识别与定位方法研究[J]. 机械设计与制造,2015(10):172-175.
APA 唐宇,吴清潇,&朱枫.(2015).平面工件的识别与定位方法研究.机械设计与制造(10),172-175.
MLA 唐宇,et al."平面工件的识别与定位方法研究".机械设计与制造 .10(2015):172-175.
Files in This Item:
File Name/Size DocType Version Access License
平面工件的识别与定位方法研究.pdf(643KB)期刊论文出版稿开放获取ODC PDDLView Application Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[唐宇]'s Articles
[吴清潇]'s Articles
[朱枫]'s Articles
Baidu academic
Similar articles in Baidu academic
[唐宇]'s Articles
[吴清潇]'s Articles
[朱枫]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[唐宇]'s Articles
[吴清潇]'s Articles
[朱枫]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 平面工件的识别与定位方法研究.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.