Recognition of parking spaces on dry and wet road surfaces using received light intensity of laser for ultra small EVs

Research and development of automatic driving technology has been actively conducted in recent years. Under this background, it is considered that the car parking problem is expected to be developed for supporting drivers to complete automatic parking. Many parking lots in an urban area prepare parking spaces with asphalt road surface drawn by white paint. Research to recognize parking spaces using camera images has been conducted so far. However, camera images are known to be not robust to environmental conditions such as nighttime and a backlight. Therefore, a method of recognizing parking spaces is proposed so that it can be used even when the use time is day or night, irrespective of whether the road surface is dry or wet. In the proposed method, the road surface is classified using the statistical model of the received light intensity value of laser range scanner. Then, the target parking position is estimated by Hough transformation.