A corner detection method in a pseudo-random structured light pattern

This paper describes a corner detection method in a pseudo-random structured light pattern. In the algorithm, the image is firstly convoluted with a weighted Gaussian mask (WGM) in which the symmetry property between two neighboring rhombic elements is considered. As a result, the proposed method is more suitable to detect the X shape corner in the structured light pattern. Then a non-maximal suppression process is carried out to find the candidates for the corner. Record the times of each position being the candidate in different size of WGMs. Finally, the fuzzy c-means (FCM) algorithm is conducted to determine the threshold for being the corner. Some experiments have been conducted to demonstrate the effectiveness of the proposed method.