Intelligent Transportation Systems is a rapidly evolving and extensively researched field. The development of tools and methods necessitated the appearance of a new concept, Cognitive Mobility, covers greater integration of transport related areas. Our research goes beyond simple image processing and statistical analysis and includes cognitive elements of mobility, for example, gives methods for adaptive analysis of typical vehicle behavior in junctions and helps in decision making for better utilization of infrastructure. In this work, we present an adaptive approach to interpreting traffic scenes. This approach uses the YOLOv7 object detector and DeepSORT tracking algorithm to generate trajectories of moving vehicles in video recordings captured from a stationary viewpoint. The paper examines and compares various techniques for clustering the vehicle trajectories, such as using clustering algorithms to group vehicles based on their entry and exit points within the video scene. Furthermore, we report the results of clustering parameter sensitivity tests performed on the video dataset we created. This control over the granularity of the clustering enables generating street-level or lane-level traffic data from the same recordings. Finally, we demonstrate some practical applicability of the method through illustrative examples, showcasing how the generated traffic data can be used to monitor and analyze traffic patterns, identify congestion points, and inform transportation planning and decision-making.
Adaptive Vehicle Trajectory Clustering Based on Computer Vision
Lect. Notes in Networks, Syst.
IEEE International Conference on Cognitive Mobility ; 2024 ; Budapest, Hungary October 07, 2024 - October 08, 2024
25.02.2025
17 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Vision Based Vehicle Trajectory Supervision
British Library Conference Proceedings | 2000
|Vision based vehicle trajectory supervision
IEEE | 2000
|Similarity Based Vehicle Trajectory Clustering and Anomaly Detection
British Library Conference Proceedings | 2005
|Adaptive Density Ship Trajectory Clustering Based on AIS data
Springer Verlag | 2024
|