于铁军, 刘立峰, 邢彦锋, 蒋世谊.基于角点检测的焊缝图像ROI优化提取算法[J].轻工机械,2021,39(4):80-83 |
基于角点检测的焊缝图像ROI优化提取算法 |
Optimized ROI Extraction Algorithm for Weld Image Based on Corner Detection |
|
DOI:10.3969/j.issn.1005 2895.2021.04.015 |
中文关键词: 实时检测 Moravec算法 角点检测 ROI提取 |
英文关键词:real time detection Moravec algorithm corner detection ROI(region of interest) extraction |
基金项目: |
|
摘要点击次数: 620 |
全文下载次数: 899 |
中文摘要: |
为了解决焊缝表面缺陷检测中使用点云数据过于庞大而导致检测时间过长的问题,课题组针对Moravec角点检测算法进行优化,使用优化后的角点检测算法对激光中心线进行特征点提取并确定感兴趣区域(region of interest,ROI)。经过实验表明:优化后的角点检测算法能够有效避免伪角点的出现,提高了鲁棒性,同时经过ROI提取后的焊缝点云数据量减少了71.14%。该方法能够有效解决计算基于点云的焊缝表面缺陷检测数据量过大的问题。 |
英文摘要: |
In order to solve the problem that the point cloud data used in the weld surface defect detection is too large [JP2]and the detection time is often too long, the Moravec corner detection algorithm was optimized and the optimized algorithm was used to extract feature points of the laser center line and determine the ROI. The experimental results show that the optimized corner detection algorithm can effectively avoid the appearance of false corner and improve the robustness. At the same time, the amount of weld point cloud data extracted by ROI can be reduced by 71.14%. This method can effectively solve the problem that the amount of weld surface defect detection data based on point cloud is too large. |
查看全文 查看/发表评论 下载PDF阅读器 |
关闭 |