Coherent traffic monitoring is pivotal for facilitating interstate and highway safety and efficiency. In such areas, the incorporation of small Uncrewed Aerial Systems (sUASs) coupled with computer vision (CV) and deep learning (DL) techniques is growing in popularity. Manual or sensor-based traffic monitoring systems often have limited coverage areas and are challenging to use for real-time traffic issue monitoring, while sUASs provide a wider view of traffic flow, faster deployment, and near-to-real-time monitoring of traffic patterns and vehicle tracking using state-of-the-art DL-based detection and CV-based tracking algorithms. This paper provides a case study with a comparative analysis of the performance of a YOLOv11-based object detection model integrated with two tracking algorithms, StrongSORT and ByteTrack, for tracking vehicles. These algorithms are analyzed using object detection and multiple object-tracking performance metrics. The findings of this study demonstrated a potential application of the studied algorithms in everyday vehicle tracking and traffic surveillance deployment.
Comparative Case Study: Traffic Monitoring Using YOLOv11-Based Object Detection and Two Tracking Algorithms with Small Uncrewed Aerial Systems
International Conference on Transportation and Development 2025 ; 2025 ; Glendale, Arizona
2025-06-05
Conference paper
Electronic Resource
English