Preceding vehicle detecting and tracking for intelligent vehicles

An improved monocular vision method is studied for intelligent vehicle to detect the preceding car in the structural road environment. Through identifying the edges of the car, the object is detected; the false object is eliminated and the eligible object expressed as a 2-D model is acquired. Then the location of object in the next frame is predicted by Kalman filter, and the object is detected near that location. Finally a novel likelihood function is desired to verify the tracking results. Experiment results of the image sequence from PETS2001 showed that the method can detect and track the preceding car automatically, rapidly and exactly.