Open AccessAn accurate method for detecting moving circular face with chamfer in video
Author(s) -
Sung−Wook Min,
Baofu Li
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/677/5/052092
Subject(s) - ellipse , chamfer (geometry) , artificial intelligence , computer vision , computer science , interference (communication) , face (sociological concept) , joint (building) , basis (linear algebra) , mathematics , geometry , channel (broadcasting) , engineering , architectural engineering , computer network , social science , sociology
A Circle is a common shape in mechanical parts, which projects as ellipse in image or video. In industrial video, target ellipse is often chaotic due to chamfer interference and external interference. An algorithm is proposed to precisely detect ellipse in video on basis of arc analysis in this paper. Compared with the previous methods, the algorithm adds the step of re-extracting the omitted arcs in first detection, and distinguishes target from interference, so it is more accurate. Combined with a video about the fatigue experiment of self-lubricating joint bearing to analyze, the effectiveness and accuracy of this algorithm are verified intuitively.