A Visual Control System Using Image Processing and Fuzzy Theory

Abstract

We developed a visual control system for an unmanned vehicle. The system consists of a dynamic image processor and a fuzzy logic control mechanism. It quickly recognizes markers lined along a road and thereby navigates a driverless vehicle. The markers are detected in real time by pipeline processing in the color identification processor and logical filter; the marker sequence is recognized by an improved Hough transform, then the fuzzy logic control mechanism decides the steering angle. To use the information on the movement of the vehicle, we constructed fuzzy inference rules on how position changes with time. We developed an LSI (large-scale integrated circuit) chip for the logical filter to realize a very compact and practical system (23 × 30 × 9.5 cm). We mounted this system on a vehicle, and it successfully drove around a test track.