Dávid Papp and Regő Borsodi
Determining Hybrid Re-id Features of Vehicles in Videos for Transport Analysis
The research topic presented in this paper belongs to computer vision problems in the transport application area, where the statistical data of the results give the input for the transport analysis. Although object tracking in a controlled environment could be performed with good results in general, accurate and detailed annotation of vehicles is a common problem in traffic analysis. Such annotation includes static and dynamic attributes of numerous vehicles. Most recent object trackers employ CNNs to compute the so-called re-identification features of the bounding boxes. In this paper we introduce hybrid re-identification features, which combine latent, static, and dynamic attributes to improve tracking. Furthermore, we propose a lightweight solution that could be integgrated in a real-time multi-camera tracking system.
Please cite this paper the following way:
Dávid Papp and Regő Borsodi, "Determining Hybrid Re-id Features of Vehicles in Videos for Transport Analysis", Infocommunications Journal, Vol. XIV, No 1, March 2022, pp. 17-23., https://doi.org/10.36244/ICJ.2022.1.3