REAL TIME EFFICIENT VEHICLE SPEED MONITORING AND TRAFFIC SURVEILLANCE SYSTEM USING DEEP LEARNING
DOI:
https://doi.org/10.48047/znnhwa30Keywords:
Deep learning, YOLOv10, transformer fusion, uncertainty quantification, evidential deep learning, federated learning, edge computing, intelligent transportation systemsAbstract
Real-time vehicle speed monitoring and traffic surveillance are critical for reducing urban accidents, yet existing deep learning systems struggle with low-resolution CCTV, occlusions, and variable frame rates in diverse Indian traffic.
This paper introduces the Uncertainty-Guided Hybrid YOLOv10-Transformer (UGHYT) framework, which fuses optical flow transformers for robust detection/tracking, evidential deep learning for probabilistic speed regression, and federated edge distillation for deployment on resource-constrained CCTV nodes. Evaluated on MITS dataset (94.1% mAP) and custom 50-hour Bhopal CCTV corpus (3.8 km/h RMSE, 35 ms latency), UGHYT outperforms YOLOv8/9 baselines by 35% in speed accuracy under 70% occlusion and 480p conditions.
UGHYT enables scalable IoT-edge integration for smart cities, supporting anomaly alerts and adaptive signals. Future federated learning across regions promises cross-domain robustness for safer transportation.
Downloads
References
J. Kim, Y. H. Mo, and S. H. Park, “A real-time vehicle counting, speed estimation, and traffic light optimization system using deep learning,” J. Adv. Transp., vol. 2021, pp. 1–15, Oct. 2021.
W. Luo et al., “Single-camera and inter-camera vehicle tracking and speed estimation based on fusion of vision and mmWave radar,” IEEE Access, vol. 9, pp. 45806–45819, 2021.
S. T. N. Tran et al., “A framework for real-time vehicle counting and velocity estimation using deep learning,” Sustain. Cities Soc., vol. 102, p. 105234, Feb. 2024.
S. Li et al., “Vehicle speed detection system utilizing YOLOv8 and DeepSORT,” arXiv, arXiv:2406.07710, Jun. 2024.
A. Kumar et al., “A multi-stage deep learning approach for real-time vehicle detection and speed estimation,” PMC, Jul. 2025.
R. Wang et al., “Deep learning-based vehicle speed estimation in bidirectional traffic,” Procedia Comput. Sci., vol. 235, pp. 1234–1242, 2024.
M. Ahmed, “Enhanced traffic surveillance: YOLO-based speed estimation,” J. Netw. Autom. Optim., vol. 15, no. 1, pp. 60–70, 2024.
Z. Chen et al., “Automating traffic monitoring with SHM sensor networks via vision-supervised deep learning,” arXiv, arXiv:2506.19023, Jun. 2025.
Ultralytics, “Speed estimation using Ultralytics YOLO,” Ultralytics Docs, Jan. 2026.
A. Lal et al., “Review of object detection for traffic surveillance,” Int. J. Electr. Comput. Eng., vol. 14, no. 5, pp. 7890–7900, 2024.
IEEE, “Real-time traffic surveillance using DL,” IEEE Xplore, May 2023.
S. Patel, “YOLO for vehicle speed in urban India,” J. Intell. Syst. Eng. Manag., 2025.
R. Wang et al., “Deep learning-based vehicle speed estimation in bidirectional traffic,” Procedia Comput. Sci., vol. 235, pp. 1234–1242, 2024.
A. Kumar et al., “A multi-stage deep learning approach for real-time vehicle detection and speed estimation,” PMC, Jul. 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Mohit Tiwari, Dr. Vikas Sakalle (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
