Optimizing YOLOv8 for Parking Space Detection: Comparative Analysis of Custom YOLOv8 Architecture
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913854978523136 |
|---|---|
| author | Pokhrel, Apar Dao, Gia |
| author_facet | Pokhrel, Apar Dao, Gia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing YOLOv8 for Parking Space Detection: Comparative Analysis of Custom YOLOv8 Architecture Pokhrel, Apar Dao, Gia Computer Vision and Pattern Recognition 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. |
| title | Optimizing YOLOv8 for Parking Space Detection: Comparative Analysis of Custom YOLOv8 Architecture |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.17364 |