Enhancing automotive safety through advanced object behaviour tracking for intelligent traffic and transport system

In the ever-evolving landscape of vehicle motion analysis, the imperative for enhanced road safety has underscored the importance of tracking object behavior, with a particular focus on vehicles. This paper proposes an innovative approach specifically designed for tracking vehicle behavior, emphasizing collision risk analysis. Central to this approach is the development of a powerful model for meticulous vehicle detection and classification, using real-world video feeds. By leveraging the YOLO algorithm, our method achieves real-time object detection, which is crucial for effective traffic monitoring. We extend our work beyond simple detection to include trajectory tracking, wherein we analyze the complexities of vehicle movement to identify patterns of traffic behavior and potential congestion hotspots. To refine our system further, we have integrated the DeepSORT algorithm, which applies the Kalman Filter and Hungarian algorithm to achieve enhanced multi-object tracking. This allows for seamless tracking through occlusions and at intersections. Our system is adept at identifying potential collision risks by employing advanced risk analysis techniques that assess severity and predict possible incidents. This paves the way for robust preventative measures and underscores our commitment to improving road safety, reducing accidents, saving lives, and enhancing traffic flow. As urban environments grow, such technological advancements are poised to make a significant impact on traffic management and safety standards. We have validated our system's performance using comprehensive datasets, showcasing marked improvements in detection accuracy, precision, and tracking capabilities under various conditions. The development and successful validation of our system not only confirm the viability of our approach but also lay the foundation for future developments in object-tracking technology for autonomous systems.