A Color Tracker Employing a Two-dimensional Color Histogram Under Unstable Illumination

This paper describes a robust technique for detecting and tracking an object by color information employing a camera-computer system. Visual sensing techniques are indispensable tools for realizing an intelligent robot having artificial eyes and a brain. The difficulties of employing color information in various computer vision problems is, however, it is not a very stable feature to be detected, since it is normally influenced by illumination conditions caused by weather, time in a day, lights, shade, etc. A robust color detection technique hasn't been proposed yet in the computer vision field. In this paper, a robust color tracking is achieved by updating the color model employing two-dimensional histogram of the h-s plane of the hsv color space. The proposed technique is effective even under unknown illumination change because the color model is acquired directly from the object and it is updated repeatedly. The technique is implemented on a pan-tilt camera and a computer system and it tracks a specified color object in a robust manner