Image-Based Approach for Parking-Spot Detection with Occlusion Handling

With the aid of advanced information technology, car parking space management is evolving dramatically toward an automatic way. The most efficient approach for parking-spot detection is based on embedded sensors, which can cause a significant cost of equipment purchasing, installation, and maintenance. Therefore, a growing number of studies have been done on vision-based detection methods using cameras. This paper aims to develop a parking-spot detection method based on images captured by existing surveillance cameras at car parks. Such images are used for recognition of parking lines, parking-spot positioning, and vehicle feature extraction. The issue of vehicle occlusion due to the limited installation height of surveillance cameras in car parks is handled. With the proposed detection approach, vacant and occupied parking spots could be distinguished to provide useful information of parking-space statuses to drivers. Various experiments have been conducted with promising results in different environmental conditions, like daytime and evening, sunny and rainy days, indoor and outdoor, and low and high camera positions. The proposed approach is applicable to large-scale car parks based on an extended multicamera system.