A novel X-corner detector based on video
Qing He, Chao Hu, Lei Cui, Wei Liu, Max Q.‐H. Meng · 2009
The accuracy of corner detection is critical for many machine vision applications. A novel corner detector based on video is proposed in this paper. The corner detector can effectively constrain camera noise by using multiple frames from video. The kernel of this method is the similarity algorithm which including a special representation of binary image, a robust template, a simple similarity function and a trick for similarity function threshold. On this basis, two X-corner detectors based on video are studied in this paper. One is a sub-pixel X-corner detector using average of anchor points, and the other is pixel X-corner detector using the average of frames.