A method of recognizing objects specified by color and shape in autonomous ROBOT

When the autonomous mobile robot moves, it depends on vision system to catch the targeted objects, so vision system is one of the key technologies for intelligent robot. In order to solve the problem of recognizing objects characterized by specified color and shape in the autonomous robot, a seed fill method based on HUV model is proposed and improved in this paper. First the hue histogram and brightness histogram from a color image are obtained and analyzed. The parameter U and V can represent the main feature of a color´ but the hue loses sense when the values of RGB are very small. In this paper this shortcoming was improved through cooperating with shape. Then the objects characterized by specified color and shape were recognized effectively. Through experiments, the recognizing of targeted objects with specified color and shape were effectively realized in a variety of background, and the adaptability to changed light has been improved strongly.