Application of Digital Image Processing on Automatic Parking System

• Main Author: 呂承翰
• Other Authors: Luen-Wei Liou
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/86699136498659259974

碩士 === 國立臺灣海洋大學 === 機械與機電工程學系 === 100 === In this study, an autonomous parking system is proposed. Image of the parking space was taken from the webcam mounted on the vehicle. The image of white lines defining the parking space is separated from the background by color segmentation. Next, the image taken from an oblique view is transformed to a top-down view through perspective transformation. This image is then further processed to reduce the noise and to thinning the lines. Finally, Hough line detection algorithm is applied to identify the lines. The intersections of these lines are then evaluated to obtain the coordinates. Once the coordinates of the corners of the parking space are identified, the spatial information is used to define a suitable parking path for the vehicle. The setting of the path will depend on the relative position of the vehicle to the parking space, the turning radius of the vehicle, and the vacancies of the adjacent spaces. The strategy of generating the parking path is to first place the vehicle at a predefined starting point and then to move the vehicle along a preset path into parking space. The accuracy of parking space position identification through the image processing was demonstrated by experiments. Also, the feasibility of the proposed system was demonstrated by experiments using an autonomous vehicle.