Real Time Visual Tracking System Mimicking Saccadic Movements
Yoshinori Takeuchi, Zeng-Fu Wang, Noboru Ohnishi, Noboru Sugie
Proceedings of Second Asian Conference on Computer Vision, Vol. 1,
for the compressed PostScript file (479kbyte).
for the uncompressed PostScript file (1328kbyte).
This paper presents a real-time visual tracking system that can follow a moving
object by controlling the pan and tilt of a camera based on the object
position obtained by video-rate image processing.
The system consists of a camera, an image processing system,
a pan/tilt platform and a motor driver.
The developed platform can control the pan and tilt angle of a camera with
accuracy of 0.002 deg and speed of 50 deg/sec.
We have developed a tracking algorithm using both an edge image and a frame
subtraction image so as to be robust against noise.
The algorithm, implemented on a general purpose image processor,
can detect a moving object in less than 33 msec.
As an experimental result, the system can track a moving object in real-time.