Title :
Study on Beeline Edge Subpixel Localization for Mechanical Part
Author :
Cui, Yanping ; Ge, Xingwei ; Fu, Qifeng ; Yue, Yanfang
Author_Institution :
Sch. of Mech. & Electron. Eng., Hebei Univ. of Sci. & Technol., Shijiazhuang, China
Abstract :
Beeline is the important element in the computer vision measurement. Subpixel detection of beeline on image plane based on spatial moment and 3D reconstruction of spatial beeline was researched. First the LOG operator was used to locate the edge at the level of pixel quickly, and then the spatial moment was used to detect subpixel location of the discrete points of edge. The least square fitting was adopted to fit the subpixel edge points which have been detected by Hough transform. The validity and precision of spatial moment subpixel edge detection and the detection of beeline on image plane was studied. The experiments show that spatial moment subpixel edge detection and the detection of beeline on image plane have acquired high precision.
Keywords :
Hough transforms; computer vision; edge detection; image reconstruction; least squares approximations; mechanical engineering computing; 3D spatial beeline reconstruction; Hough transform; beeline edge subpixel localization; computer vision measurement; least square fitting; mechanical part; spatial moment; subpixel detection; Computer vision; Convolution; Discrete transforms; Image edge detection; Image reconstruction; Interpolation; Least squares methods; Measurement techniques; Mechanical variables measurement; Moment methods;
Conference_Titel :
Image and Signal Processing, 2009. CISP '09. 2nd International Congress on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4244-4129-7
Electronic_ISBN :
978-1-4244-4131-0
DOI :
10.1109/CISP.2009.5304610
