抄録
Automobile technologies have been challenging to realization of safe driving by the employment of a computer vision system. Various techniques have been developed for preventing car accidents based on so-called car vision technologies. We propose in this paper a technique for detecting pedestrians on a zebra crossing near a traffic junction from the video images provided by a camera mounted on a car. The detection is performed by recovering backgrounds from the video images and separating foregrounds from the backgrounds. We also present a method of recognizing motions of the detected pedestrians by referring to a developed motion data base. Performance of the proposed techniques is shown by the experiments employing outdoor video images.
