Spatio-Temporal Vehicle Re-Identification for Intelligent Traffic Systems

• Artur Henrique do Nascimento Souza UFES / Atman Systems http://orcid.org/0009-0009-2732-7445
• Raquel Frizera Vassallo UFES https://orcid.org/0000-0002-4762-3219
• Augusto Abling UFES / Atman Systems

DOI: https://doi.org/10.5753/sbrc_estendido.2025.5955

Abstract

Most computer vision systems implemented in the context of urban monitoring rely on metrics obtained from isolated cameras, which limits large-scale analysis capabilities. This work proposes a modular and lightweight system capable of operating on embedded devices in a decentralized manner, enabling the generation of new correlated data across multiple monitoring points. With this approach, it becomes possible to obtain metrics such as travel times and most-used routes, contributing to improved traffic management and strategic urban planning.

Keywords: Deep Learning, Intelligent Traffic Systems, Computer Vision, Edge Processing

References

Bewley, A., Ge, Z., Ott, L., Ramos, F., and Upcroft, B. (2016). Simple online and realtime tracking. In 2016 IEEE International Conference on Image Processing (ICIP).

Kim, H.-G., Na, Y., Joe, H.-W., Moon, Y.-H., and Cho, Y.-J. (2023). Spatial-temporal vehicle re-identification.

Lv, K., Du, H., Hou, Y., Deng, W., Sheng, H., Jiao, J., and Zheng, L. (2019). Vehicle re-identification with location and time stamps. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.

Montoia, V. (2024). Mercado automotivo brasileiro é o que mais cresce no mundo em 2024, diz ANFAVEA. Acessado em: 26 dez. 2024.

Shahgholian, M. and Gharavian, D. (2018). Advanced traffic management systems: An overview and a development strategy.

Singh, B. and Gupta, A. (2015). Recent trends in intelligent transportation systems: A review. Journal of Transport Literature, 9(2):30–34.

Tomasiello, D. B., Pereira, R. H. M., and Nadalin, V. G. Os impactos desiguais do congestionamento urbano no acesso a empregos. Texto para Discussão, (2922).

Varghese, R. and M., S. (2024). YOLOv8: A novel object detection algorithm with enhanced performance and robustness. In 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pages 1–6.

Wang, H., Hou, J., and Chen, N. (2019). A survey of vehicle re-identification based on deep learning. IEEE Access, 7:172443–172469.

Wang, Z., Wang, L., Shi, Z., Zhang, M., Geng, Q., and Jiang, N. (2024). A survey on person and vehicle re-identification. IET Computer Vision.

Zhou, K., Yang, Y., Cavallaro, A., and Xiang, T. (2019). Omni-scale feature learning for person re-identification.