An Efficient and Cost-Effective Vehicle Detection and Tracking System for Collision Avoidance in Foggy Weather
An Efficient and Cost-Effective Vehicle Detection and Tracking (ECE-VDT) system is proposed and is essential for real-time collision avoidance and driver assistance in foggy weather conditions. The proposed ECE-VDT system encompasses an optimized SimYOLO-V5s algorithm and its five variants for vehic...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11078259/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | An Efficient and Cost-Effective Vehicle Detection and Tracking (ECE-VDT) system is proposed and is essential for real-time collision avoidance and driver assistance in foggy weather conditions. The proposed ECE-VDT system encompasses an optimized SimYOLO-V5s algorithm and its five variants for vehicle detection, while the optimized deep-SORT algorithm is proposed for vehicle tracking. Several design changes are proposed to enhance the SimYOLO-V5s variants, aiming to optimize the baseline YOLO-V5s algorithm. The backbone network of the baseline YOLO-V5s algorithm is optimized by integrating the SimSPPF module, a variant of the standard SPPF module. Furthermore, diverse distance metrics and loss functions, such as CIOU, DIOU, EIOU, GIOU, and SIOU, are considered to enhance the baseline YOLO-V5s bounding box localization accuracy. These design changes significantly improved the baseline YOLO-V5s vehicle detection performance. The optimized deep-SORT algorithm is proposed by utilizing the SiLU activation function in the CNN network of the baseline deep-SORT algorithm, compared to the ReLU activation function. The self-annotated and customized state-of-the-art foggy weather vehicle detection datasets, Vehicle Detection in Adverse Weather Nature (DAWN), Foggy Driving (FD), and Foggy Cityscapes (FC), are considered for evaluating the vehicle detection performance of baseline and SimYOLO-V5s variants in adverse weather conditions. Extensive and rigorous experiments on cloud and local GPU-enabled systems show that the optimized SimYOLO-V5s variants, more specifically SimYOLO-V5s_GIOU outperformed in mAP50 multi-class vehicle detection by <inline-formula> <tex-math notation="LaTeX">$1.6~\%$ </tex-math></inline-formula> on the DAWN dataset, <inline-formula> <tex-math notation="LaTeX">$15.2~\%$ </tex-math></inline-formula> on the FD dataset, and <inline-formula> <tex-math notation="LaTeX">$3.4~\%$ </tex-math></inline-formula> on the FC dataset compared to baseline YOLO-V5s. The optimized SimYOLO-V5s variants also outperformed state-of-the-art algorithms in accuracy and speed. The optimized deep-SORT outperforms pre-processing, inference, NMS post-processing, and update time, achieving higher FPS on foggy and the BDD100K dataset video sequences compared to the baseline deep-SORT and strong-SORT vehicle tracking algorithms. The proposed ECE-VDT system is an efficient and cost-effective solution to assist human-centric drivers of low-end vehicles and autonomous vehicles to avoid road collisions in foggy weather. |
|---|---|
| ISSN: | 2169-3536 |