Optimizing YOLOv8 for Parking Space Detection: Comparative Analysis of Custom YOLOv8 Architecture
This work addresses parking management systems by improving detection for borderline cases, but it is incremental as it builds on existing YOLOv8 methods.
The paper tackled the problem of parking space occupancy detection by comparing customized backbone architectures integrated with YOLOv8, finding that different backbones like ResNet-18 and EfficientNetV2 offer trade-offs in accuracy and efficiency on the PKLot dataset.
Parking space occupancy detection is a critical component in the development of intelligent parking management systems. Traditional object detection approaches, such as YOLOv8, provide fast and accurate vehicle detection across parking lots but can struggle with borderline cases, such as partially visible vehicles, small vehicles (e.g., motorcycles), and poor lighting conditions. In this work, we perform a comprehensive comparative analysis of customized backbone architectures integrated with YOLOv8. Specifically, we evaluate various backbones -- ResNet-18, VGG16, EfficientNetV2, Ghost -- on the PKLot dataset in terms of detection accuracy and computational efficiency. Experimental results highlight each architecture's strengths and trade-offs, providing insight into selecting suitable models for parking occupancy.