Color based object recognition, localization, and movement control for multiple wheeled mobile robots

This paper presents an experimental study on object recognition, localization and movement control of soccer robots using a vision system. A color image segmentation method based on YUV color information of each pixel of the color image is applied to the recognition of position and orientation of a small mobile robot. First the lower and higher threshold values of Y, U, and V are determined for the sample color markers. Then color image segmentation is performed using the tables that transform each value of Y, U, and V in a pixel to membership data in several color classes. The position and orientation of the robots and ball on the field are efficiently and accurately recognized by calculating the center of gravity of each extracted color region. Experimental results of real-time movement control and ball handling are also presented.