Edge extraction of shaft part based on combination of double threshold and shape constraint

It is the first step to complete edge detection of shaft part for the pose detection task. According to the characteristics of the shaft part image, an algorithm to improve contour detection is presented based on double thr eshold to extract the outline of shaft part. Freeman chain code is used to connect edge points for obtaining integrated contour information. The straightness of shaft image generatrix is improved with linear fitting based on Hough transform. The experiment demonstrates that the proposed scheme can effectively eliminate useless marginal information, which is nothing to do with the target. Straight line fitting precision of the shaft image generatrix is improved. The extracted boundary is more clear and accurate compared with several existing algorithms. The research provides important informations for the follow-up pose detection of shaft part.