A novel dynamic edge detection inspired from mammalian retina toward better robot vision

摘要

Edge detection plays a significant role in assessing the capability level of the robot's vision. Accurate edge detection leads to better vision. The work in this paper was conducted by the inspiration of the biological concept of mammalian vision. That is, the retina enriches the edges in the view before passing it to the visual cortex in the brain for further processes. Although many works have been done to investigate surrounding this issue, these works are still limited in compare with that exists in retina. In this study, we investigated the main role of horizontal cells for the retina's network toward building a retina-like robot's vision technique. Experimental results show the validity of the proposed algorithm to provide accurate edges in real-time with less noise.