Smart Parking Space Detection Using YoLo and Computer Vision for Open-Space University Parking

The increasing demand for parking space on university campuses has created a need for a smart solution to efficiently manage and identify available parking slots. This study proposes a Smart University Parking Space Recognition System that leverages computer vision and the YOLO (You Only Look Once) algorithm to detect parked vehicles in a single-level, open-space parking area. However, when applying YOLO to such environments, several challenges arise, including occlusions, lighting variations, and object overlaps that can lead to false detections. These concerns are addressed by optimizing YOLO parameters and validating performance with actual camera footage. The proposed system utilizes CCTV cameras, a Raspberry Pi, and a display monitor to provide real-time parking status, offering a scalable, costeffective solution for managing campus parking congestion. The results show an accuracy of 91.87 % and precision of $\mathbf{9 4. 8 4 \%}$, confirming the system's feasibility and effectiveness.