DEVELOPMENT OF A ROAD OBSTACLE SENSOR COMBINING IMAGE PROCESSING AND A LASER RADAR

This paper presents a new obstacle sensor, comprised of an image processing system and a laser radar, that is able to detect smaller objects more reliably than conventional sensors. The system uses image processing to detect obstacles based on the difference between the background image and the input image. This new background subtracting image allows the optimal threshold to be set for each image. The image processing system is then complemented by incorporating a high-resolution laser radar to achieve an obstacle sensor providing a very reliable obstacle evaluation performance which takes into account information regarding the brightness and the detected distance of each point.