基于增强模板的鞋体涂胶特征点快速匹配提取  

FAST MATCHING AND EXTRACTION OF FEATURE POINTS FOR SHOE GLUINGBASED ON ENHANCED TEMPLATE

在线阅读下载全文

作  者:申启访 杨煜俊[1,2] 肖旺 李杰诚 Shen Qifang;Yang Yujun;Xiao Wang;Li Jiecheng(CIMS Laboratory,School of Mechanical and Electrical Engineering,Guangdong University of Technology,Guangzhou 510006,Guangdong,China;Guangzhou GREATOO Robot and Intelligent Manufacturing Research Institute,Guangzhou 510530,Guangdong,China)

机构地区:[1]广东工业大学机电工程学院CIMS实验室,广东广州510006 [2]广州巨轮机器人与智能制造研究院,广东广州510530

出  处:《计算机应用与软件》2023年第8期244-249,336,共7页Computer Applications and Software

基  金:广东省重点领域研发计划项目(2019B090916002);广州市科技计划项目(201902010054)。

摘  要:拖鞋自动化生产装配中,胶水喷涂是最重要的环节,由于拖鞋鞋体为特定局部区域侧面喷涂,以及颜色不一、挤压形变和环境光变等因素,涂胶区域的图像特征提取变得尤为困难。应用3D激光相机进行鞋体图像采集,避免环境光变对图像的影响,通过调整相机曝光以及相机安装方式等解决像素跳动或缺失的问题,采取基于边缘特征的增强模板匹配的方法,对涂胶特征区域进行匹配定位,结合曲率尺度空间的角点提取方式,精准快速地实现涂胶特征点提取。实验结果表明,该方法针对不同鞋码不同颜色鞋体都具有良好的适用性与稳定性,实现快速检测,满足实际生产需求。In the automatic production and assembly of shoes,glue spraying is the most important part.Due to factors such as the difference of the shoe color,extruding deformation and environmental light change,especially its gluing is on the side of a special area,it is particularly difficult to extract the image feature of the glued area.In this paper,3D laser camera was used for image acquisition,which avoided the influence of environmental light change on image quality.The problems such as pixel bounce or missing were solved by adjusting the exposure of the camera and its installation mode.The enhanced method based on edge feature template matching was adopted to locate the glued feature area.Combined with the corner point extraction method of the curvature scale space,the glue feature point extraction was accurately and quickly realized.The experimental results show that this method has good applicability and stability for shoes in various shapes and colors,and it realizes fast detection and meets real production needs.

关 键 词:边缘特征 增强模板 特征匹配 角点提取 鞋体涂胶 

分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象