Abstract
Locating and classifying different types of vehicles is a vital element in numerous applications of automation and intelligent systems ranging from traffic surveillance to vehicle identification, with deep learning models now dominating the field of vehicle detection. However, vehicle detection in Bangladesh remains a relatively unexplored research lacuna. One of the main goals of vehicle detection is its real-time application, with “You Only Look Once” (YOLO) models proving to be the most effective. This paper compared real-time vehicle highway detection systems using YOLOv4, Faster R-CNN and SSD algorithms to determine the best performance. A vehicle detection and tracking system was also developed that improved highway safety. Vehicle trials compared the real-time performances of the YOLO, Faster R-CNN and SSD algorithms in detecting and tracking highway vehicles by measuring precision, recall, F1-score and operating speed. Models for each algorithm were constructed and each model was trained and tested, with performance measured using a confusion matrix. This statistical tool assessed the efficiency of the system using a prepared test dataset and evaluated the results using appropriate indicators such as real-time road lines, traffic signs and vehicle detection false positive rates. Results showed that the YOLOv4 algorithm outperformed Faster R-CNN and SSD in real-time vehicle detection and tracking on highways. YOLOv4 also processed the results more quickly and proved superior in detecting and tracking objects in real time. The Faster R-CNN algorithm gave high object detection, tracking accuracy and recall while reducing the number of locations needing detection, with the SSD algorithm providing high precision, recall and good image detection results.
Publisher
Rajamangala University of Technology Thanyaburi
Reference42 articles.
1. Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016;2016:779-788. doi: 10.1109/CVPR.2016.91.
2. Redmon J, Farhadi A. YOLOv3: An incremental improvement. arXiv preprint arXiv. 2018; doi: 10.48550/arXiv.1804.02767.
3. Bochkovskiy A, Wang CY, Mark Liao HY. YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv. 2020;2004.10934.
4. Ren S, He K, Girshick R, Jian Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 2015;2015:91-9.
5. Girshick R. R-CNN F. In Proceedings of the IEEE international conference on computer vision. 2015;1440-8.