Abstract
This paper deals with evolutionary robot vision based on a genetic algorithm and fuzzy evaluation in order to realize people tracking. Active robot vision is an important research topic, and we must improve the performance of the visual perception. First, we discuss the concept of evolutionary robot vision in dynamic environments. Next, we apply growing neural gas for preprocessing as a bottom-up processing, and a local genetic algorithm based on clustering for template matching in human face recognition as a top-down processing. Furthermore, in order to improve the performance of the human face detection, we use fuzzy evaluation for evaluating the degree of human face. Finally, we show several experimental results of the proposed method and discuss the effectiveness of the proposed method.