Vision-Based Parking Space Detection: A Mask R-CNN Approach

Abstract

The rapid increment of vehicles and the inefficient management of available parking spaces lead to traffic congestion and resource waste in urban areas. Thus, there is an urgent need to develop an intelligent parking system to find out suitable parking spaces quickly. To this end, we elaborate on various object detection algorithms and parking space detection methods. Then, we propose a novel vision-based parking space detection system with a Mask R-CNN approach. It can be applied in various scenarios and infer parking spaces from the positions of the parked vehicles. Experimental results have shown that the proposed system performs well in large car parks and reduces the human effort in image processing. This study provides a successful paradigm for future intelligent parking systems, and it can also effectively promote the development of smart cities.