Amirgaliyev B., Mussabek M., Zhumadillayeva A., Baishemirov Z.
Enhancing mobility in smart cities: people counting and characteristics detection in public buses // Proceedings of the 2025 IEEE European Technology and Engineering Management Summit (E-TEMS). — 2025. — Conference held 26–28 May 2025. — DOI: 10.1109/E-TEMS64751.2025.11239318.

Abstract: Detecting passengers and tracking them in public transport is a critical task in smart city environments. This study focuses on people counting and passenger tracking using computer vision techniques. The FairMOT hybrid model, which integrates detection and re-identification into a single network, is evaluated for passenger flow analysis in public buses. The model is trained on 180 videos comprising 70,710 frames of open-source bus passenger data. Experimental results show high tracking performance, achieving a recall of 97.9%, MOTA of 82.5%, and IDF1 of 73.6%. The system demonstrates strong accuracy and computational efficiency, providing a scalable solution for transit operators to optimize passenger flow monitoring and improve smart city mobility management.

Link / DOI: https://doi.org/10.1109/E-TEMS64751.2025.11239318