LAUSR

An auto-parking system is one of the promising technologies to reduce accidents and enhance driver convenience in parking lots. To accomplish collision-free parking, precise and robust parking space detection is required. However, harsh conditions such as varied illumination in outdoor parking lots and high reflection in indoor parking lots degrade the reliability of parking space detection. In this paper, we propose a unified structure for parking space detection to detect parking slot markings and static obstacles. A fully convolutional network for semantic segmentation can immediately identify free spaces, slot markings, vehicles, and other objects without using a range sensor or 3D reconstruction algorithm. Furthermore, a vertical grid encoding method can simultaneously detect unoccupied slots identified by parking slot markings and empty spaces created by surrounding static objects without sensor fusion. Experimental results show the robustness of the proposed method in various different parking scenarios. Even in challenging conditions such as dark shaded or high-glare areas, the detection performance maintains a precision rate of 96.81% and recall rate of 97.80%.