Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50
Conference paper
Pal, S. and Dagiuklas, T. (2023). Benchmarking Reidentification in Multi-Camera Tracking Systems with YOLOv8 and ResNet-50. 2023 International Conference on Human-Centered Cognitive Systems (HCCS). Cardiff, UK 16 - 17 Dec 2023 IEEE. https://doi.org/10.1109/hccs59561.2023.10452624
Authors | Pal, S. and Dagiuklas, T. |
---|---|
Type | Conference paper |
Abstract | The aim of this paper is to benchmark reidentification within a multi-camera tracking system. This benchmark has been carried out by leveraging transfer learning, utilizing YOLOv8 for real-time object detection and ResNet-50 for feature extraction. The objective is to evaluate the system's performance in accurately reidentifying vehicles across multiple cameras in real-world traffic surveillance scenarios. This benchmarking endeavor aims to provide an evaluation framework for assessing the capabilities and limitations of vehicle reidentification techniques, with a focus on their applicability in challenging conditions such as low- light environments, image compression, and object occlusions. |
Keywords | Vehicle Reidentification, Multi-Camera Tracking, Object Detection, Feature Extraction, Transfer Learning, Intelligent Transportation Systems. |
Year | 2023 |
Publisher | IEEE |
Digital Object Identifier (DOI) | https://doi.org/10.1109/hccs59561.2023.10452624 |
Accepted author manuscript | License File Access Level Open |
Publication dates | |
16 Dec 2023 | |
Publication process dates | |
Deposited | 21 Mar 2024 |
https://openresearch.lsbu.ac.uk/item/96vz9
Download files
110
total views56
total downloads0
views this month2
downloads this month