AI-Driven Real-Time Traffic Monitoring and Intelligent Control System: A Unified Deep Learning Framework for Smart Urban Mobility Management

Year : 2026 | Volume : 13 | Issue : 02 | Page : 24 33
By

Anitya Anand,

  1. Student, Department of Computer Science and Engineering, Greater Noida Institute of Technology, Uttar Pradesh, India

Abstract

Urban traffic congestion imposes staggering economic and environmental costs on modern cities, with the INRIX Global Traffic Scorecard estimating annual per-driver productivity losses exceeding $1,348 in major metropolitan areas. Conventional traffic management infrastructure—fixed-cycle signal controllers, manual surveillance, and threshold-based incident detection—is fundamentally ill-equipped to address the dynamic, non-linear complexity of contemporary urban vehicular flows. This paper introduces TrafficNet-DRL, a unified deep learning and deep reinforcement learning framework for real-time traffic monitoring, flow prediction, anomaly detection, and adaptive signal control. The proposed architecture integrates three tightly coupled subsystems: (i) a spatial-temporal graph convolutional network (ST-GCN) for multi-intersection traffic flow prediction; (ii) a YOLOv8-based multi-class vehicle detection and tracking pipeline with ReID capabilities for density estimation and incident identification; and (iii) a multi-agent deep reinforcement learning (MADRL) controller that dynamically optimizes phase durations across interconnected signalized intersections. TrafficNet-DRL is evaluated on three heterogeneous urban datasets—METR-LA, PEMS-BAY, and a newly constructed IntersectionNet-8K benchmark comprising 8,200 hours of annotated intersection footage from 24 instrumented junctions. Experimental results demonstrate a mean absolute error (MAE) of 2.14 km/h in 30-minute flow prediction, a vehicle detection [email protected] of 96.3%, and a 34.7% reduction in average intersection delay relative to Webster’s fixed-cycle baselines. The framework additionally reduces vehicular carbon emission proxies by an estimated 18.4% through idle time minimization. Collectively, these outcomes establish TrafficNet-DRL as a state-of-the-art, deployable solution for intelligent urban traffic management.

Keywords: Intelligent traffic management, deep reinforcement learning, spatiotemporal graph networks, YOLOv8 vehicle detection, adaptive signal control, urban mobility, smart city, multi-agent systems, real-time traffic monitoring, incident detection

[This article belongs to Journal of Multimedia Technology & Recent Advancements ]

How to cite this article: Anitya Anand. AI-Driven Real-Time Traffic Monitoring and Intelligent Control System: A Unified Deep Learning Framework for Smart Urban Mobility Management. Journal of Multimedia Technology & Recent Advancements. 2026; 13(02):24-33.
How to cite this URL: Anitya Anand. AI-Driven Real-Time Traffic Monitoring and Intelligent Control System: A Unified Deep Learning Framework for Smart Urban Mobility Management. Journal of Multimedia Technology & Recent Advancements. 2026; 13(02):24-33. Available from: https://journals.stmjournals.com/jomtra/article=2026/view=259952

References

  1. Bai L, Yao L, Li C, Wang X, Wang C. Adaptive graph convolutional recurrent network for traffic forecasting. Adv Neural Inf Process Syst. 2020;33:17804-15.
  2. Chu T, Wang J, Codecà L, Li Z. Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans Intell Transp Syst. 2020;21(3):1086-95. doi:10.1109/TITS.2019.2901791.
  3. Guo S, Lin Y, Feng N, Song C, Wan H. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Proc AAAI Conf Artif Intell. 2019;33:922-9. doi:10.1609/aaai.v33i01.3301922.
  4. (2024). Global traffic scorecard. [Online]. INRIX global traffic rankings. Available from: https://inrix.com/scorecard-2023/.
  5. (2023). Explore Ultralytics YOLOv8 [Online]. Ultralytics Docs. Available from: https://docs.ultralytics.com/models/yolov8.
  6. Li Y, Yu R, Shahabi C, Liu Y. Diffusion convolutional recurrent neural network: data-driven traffic forecasting [Preprint]. 2017. arXiv:1707.01926.
  7. Liang X, Du X, Wang G, Han Z. A deep reinforcement learning network for traffic light cycle control. IEEE Trans Veh Technol. 2019;68(2):1243-53. doi:10.1109/TVT.2018.2890726.
  8. Wang R, Zhang J, Wang X, He H, Zou Y. Multi-modal and multi-agent reinforcement learning framework for urban traffic flow prediction and signal control optimization. Sci Rep. 2026;16(1):7612. doi:10.1038/s41598-026-37722-5.
  9. Lv Y, Duan Y, Kang W, Li Z, Wang FY. Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst. 2015;16(2):1-9. doi:10.1109/TITS.2014.2345663.
  10. Ma X, Tao Z, Wang Y, Yu H, Wang Y. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp Res C Emerg Technol. 2015;54:187-97. doi:10.1016/j.trc.2015.03.014.
  11. Yao H, Tang X, Wei H, Zheng G, Li Z. Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction. Proc AAAI Conf Artif Intell. 2019;33:5668-75. doi:10.1609/aaai.v33i01.33015668.
  12. Varaiya P. Max pressure control of a network of signalized intersections. Transp Res C Emerg Technol. 2013;36:177-95. doi:10.1016/j.trc.2013.08.014.
  13. Zhang J, Zheng Y, Qi D. Deep spatio-temporal residual networks for citywide crowd flows prediction. Proc AAAI Conf Artif Intell. 2017;31. doi:10.1609/aaai.v31i1.10735.
  14. Zheng C, Fan X, Wang C, Qi J. GMAN: a graph multi-attention network for traffic prediction. Proc AAAI Conf Artif Intell. 2020;34:1234-41. doi:10.1609/aaai.v34i01.5477.
  15. Wojke N, Bewley A, Paulus D. Simple online and realtime tracking with a deep association metric. In: Proceedings of the IEEE International Conference on Image Processing (ICIP); 2017. p. 3645-9. doi:10.1109/ICIP.2017.8296962.
  16. Wei H, Zheng G, Yao H, Li Z. IntelliLight: a reinforcement learning approach for intelligent traffic light control. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2018. p. 2496-505. doi:10.1145/3219819.3220096.
  17. Kashinath SA, Mostafa SA, Mustapha A, Mahdin H, Lim D, Mahmoud MA, et al. Review of data fusion methods for real-time and multi-sensor traffic flow analysis. IEEE Access. 2021;9:51258-76. doi:10.1109/ACCESS.2021.3069770.
  18. Rashid T, Samvelyan M, De Witt CS, Farquhar G, Foerster J, Whiteson S. Monotonic value function factorisation for deep multiagent reinforcement learning. J Mach Learn Res. 2020;21(178):1-51.
  19. Zheng G, Xiong Y, Zang X, Feng J, Wei H, Zhang H, et al. Learning phase competition for traffic signal control. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management; 2019. p. 1963-72. doi:10.1145/3357384.3357900.
  20. United Nations. World Urbanization Prospects: 2018 Revision. New York: United Nations; 2018. Available from: https://population.un.org/wup/Publications/Files/WUP2018-Report.pdf.
  21. Wu Z, Pan S, Long G, Jiang J, Zhang C. Graph WaveNet for deep spatial-temporal graph modeling. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization; 2019. p. 1907-13. doi:10.24963/ijcai.2019/264.
Regular Issue Subscription Original Research
Volume 13
Issue 02
Received 29/06/2026
Accepted 30/07/2026
Published 15/08/2026
Publication Time 47 Days

Login

My IP

PlumX Metrics

Support