大型高温锻件在线视觉测量图像匹配方法  

Image matching method for online vision measurement of large forgings

作　　者：刘巍[1] 王亮[1] 樊超楠[1] 杨景豪[1] 徐鹏涛[1] 贾振元[1] 

机构地区：[1]大连理工大学机械工程学院,辽宁大连116024

出　　处：《激光与红外》2016年第11期1414-1418,共5页Laser & Infrared

基　　金：国家自然科学基金资助项目(No.51227004)资助

摘　　要：提出了一种大型锻件在线视觉测量图像匹配方法。本方法建立在外极线约束的基础上,根据锻件现场测量视场大实效性要求高的特点,利用双向极线的距离的方法,建立了基于极线约束的匹配判断条件。在实验室和锻造现场的实验证明本匹配方法精度高,耗时少,符合大型高温锻件在线视觉测量的要求。An image matching method for online vision measurement of large forgings is presented. The method is based on the epipolar line constraint. According to the characteristics of the wide field and the high efficiency require- ments in forging field measurement, a matching criterion is established by using the distance between the two direction polar lines. The experimental results in the laboratory and the forging field prove that this matching method is of high accuracy and less time consuming, which can meet the requirements of the online vision measurement for large high temperature forgings.

关 键 词：视觉测量 特征点匹配 外极线约束 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]