A new fast corner detection method based on template matching

Abstract Corner detection is the basic link of camera calibration, and its detection accuracy will directly affect the accuracy of camera calibration. In order to improve the extraction precision of the corners of the board, this paper put forward a new checkerboard corner detection method. Two kinds of corner point prototype templates are constructed by using the characteristics of the checkerboard. The similarity between the pixel points and the corner points is calculated by convolution of the convolution kernel and the image. The degree of similarity is used to distinguish the corner points from the non-corner points. The non-maximum suppression algorithm and the gradient statistical algorithm further screen out the target corner points. The experimental results show that the method used in this paper can accurately and quickly detect the corner position and has strong anti-interference ability.