Paper
13 June 2024 Fast vehicle detection method based on improved YOLOv5s
Jibin Li, Jinmin Zhang
Author Affiliations +
Proceedings Volume 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024); 1318044 (2024) https://doi.org/10.1117/12.3033636
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 2024, Guangzhou, China
Abstract
In order to quickly and accurately identify vehicles and pedestrians in driving scenarios, this paper proposes a fast vehicle detection algorithm SMA-YOLOv5s based on the YOLOv5s (You Only Look Once) algorithm, which introduces the lightweight backbone network ShuffleNetv2 and multi-attention mechanism. Firstly, the original backbone network of YOLOv5s is replaced with a lightweight backbone network ShuffleNetv2 to reduce the computational complexity of the model and improve the real-time performance of the model. Experimental results show that compared with the original algorithm, SMA-YOLOv5s, a lightweight model with multi-attention mechanism, reduces the floating-point arithmetic by 55.70%, loses only 1% in accuracy, only 2.6% in mAP, and improves FPS by 26.60%. With less loss of accuracy, there is less computational complexity, faster detection, and better real-time performance, making it more suitable for deployment on mobile or embedded devices with limited performance.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jibin Li and Jinmin Zhang "Fast vehicle detection method based on improved YOLOv5s", Proc. SPIE 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 1318044 (13 June 2024); https://doi.org/10.1117/12.3033636
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Object detection

Performance modeling

Data modeling

Target detection

Autonomous vehicles

Instrument modeling

Back to Top