An artificial system for visual perception in autonomous robots
Benjamin Auffarth, Yuki Muto, Y. Kunii · 2005
Image processing of natural scenes is very resource-intensive. Through the localization of salient regions, later recognition can take place more efficiently, by focusing computation-intensive processing on several areas. Our approach to designing an artificial visual system is inspired by early filtering mechanisms in the human visual system. Our technique of calculating salient regions is computationally efficient and flexible, and can be extended to other applications.