YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera
Electronics · 2024-01-04 · 13 (1) · 236
DOI: 10.3390/electronics13010236 ↗At a glance
Journal article in Electronics, published online on 2024-01-04. Written by Qiuli Liu and 3 co-authors. Cited 63 times so far (Crossref); 39 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Soft Science Research Project of Shanghai Municipal Science and Technology Innovation Action Plan, Shanghai Engineering and Technology Research Center of Shanghai Municipal Science and Technology Innovation Action Plan.
Abstract (original language)
Recently, the field of vehicle-mounted visual intelligence technology has witnessed a surge of interest in pedestrian detection. Existing algorithms for dense pedestrian detection at intersections face challenges such as high computational weight, complex models that are difficult to deploy, and suboptimal detection accuracy for small targets and highly occluded pedestrians. To address these issues, this paper proposes an improved lightweight multi-scale pedestrian detection algorithm, YOLOv8-CB. The algorithm introduces a lightweight cascade fusion network, CFNet (cascade fusion network), and a CBAM attention module to improve the characterization of multi-scale feature semantics and location information, and it superimposes a bidirectional weighted feature fusion path BIFPN structure to fuse more effective features and improve pedestrian detection performance. It is experimentally verified that compared with the YOLOv8n algorithm, the accuracy of the improved model is increased by 2.4%, the number of model parameters is reduced by 6.45%, and the computational load is reduced by 6.74%. The inference time for a single image is 10.8 ms. The cascade fusion algorithm YOLOv8-CB has higher detection accuracy and is a lighter model for multi-scale pedestrian detection in complex scenes such as streets or intersections. This proposed algorithm presents a valuable approach for device-side pedestrian detection with limited computational resources.
Funding
- National Natural Science Foundation of China
- Soft Science Research Project of Shanghai Municipal Science and Technology Innovation Action Plan
- Shanghai Engineering and Technology Research Center of Shanghai Municipal Science and Technology Innovation Action Plan
Cite
APA
Liu, Q., Ye, H., Wang, S., & Xu, Z. (2024). YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera. Electronics, 13(1), 236. https://doi.org/10.3390/electronics13010236
Vancouver
Liu Q, Ye H, Wang S, Xu Z. YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera. Electronics. 2024;13(1):236. doi:10.3390/electronics13010236
BibTeX
@article{Liu2024,
author = {Liu, Qiuli and Ye, Haixiong and Wang, Shiming and Xu, Zhe},
title = {YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera},
journal = {Electronics},
year = {2024},
volume = {13},
number = {1},
pages = {236},
doi = {10.3390/electronics13010236}
}
EUVIMED