Authors : Sachin Sharma; Mohammad Sameer Hussain; Jaspreet Kaur

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/4zefmvkx

Scribd : https://tinyurl.com/52buv8xa

DOI : https://doi.org/10.38124/ijisrt/26mar865

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Delhi experiences severe traffic congestion due to heterogeneous vehicular composition, non-lane-based driving behavior, and fixed-time signal control mechanisms. Traditional traffic systems fail to adapt to dynamic traffic patterns, leading to increased delays, fuel consumption, and environmental impact. This paper proposes an AI-driven intelligent traffic management framework integrating YOLO-based vehicle detection, LSTM-based short-term traffic flow prediction, and Reinforcement Learning-based adaptive signal control. The system utilizes real CCTV data and SUMO-based simulation to evaluate performance under realistic Delhi traffic conditions. Experimental results demonstrate a 35–50% reduction in average vehicle waiting time compared to fixed-time control strategies. The proposed framework provides a scalable and practical solution for smart city traffic optimization and can be integrated with existing Delhi Traffic Police infrastructure.

Keywords : Smart Cities, YOLO, LSTM, Reinforcement Learning, Traffic Management, AI, Delhi.

References :

1. M. Treiber and A. Kesting, “Traffic Flow Dynamics: Data, Models and Simulation,” Springer, p. 1–503, 2013.
2. Y. LeCun, Y. Bengio and G. Hinton, “Deep Learning,” Nature, p. 436–444, 2015.
3. I. Goodfellow, Y. Bengio and A. Courville, “Deep Learning,” MIT Press, p. 1–775, 2016.
4. J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 779–788, 2016.
5. S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, p. 1735–1780, 1997.
6. R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction,” MIT Press, p. 1–552, 2018.
7. N. G. Polson and V. O. Sokolov, “Deep Learning for Short-Term Traffic Flow Prediction,” Transportation Research Part C, p. 1–17, 2017.
8. L. Li, Y. Lv and F. Wang, “Traffic Signal Timing via Deep Reinforcement Learning,” IEEE/CAA Journal of Automatica Sinica, p. 247–254, 2016.
9. H. Van Hasselt, A. Guez and D. Silver, “Deep Reinforcement Learning with Double Q-learning,” Proceedings of AAAI Conference on Artificial Intelligence, p. 2094–2100, 2016.
10. W. Wei and e. al., “CoLight: Learning Network-Level Cooperation for Traffic Signal Control,” Proceedings of CIKM, p. 1913–1922, 2019.
11. M. El-Tantawy and B. Abdulhai, “Multiagent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers,” IEEE Transactions on Intelligent Transportation Systems, p. 44–52, 2015.
12. M. Behrisch, L. Bieker, J. Erdmann and D. Krajzewicz, “SUMO—Simulation of Urban Mobility: An Overview,” Proceedings of SIMUL Conference, p. 63–68, 2011.
13. D. Krajzewicz and e. al., “Recent Development and Applications of SUMO – Simulation of Urban Mobility,” International Journal of Intelligent Transportation Systems Research, p. 1–12, 2012.
14. S. D. Team, “Simulation of Urban Mobility Documentation,” SUMO Official Documentation, p. Online Resource, 2023.
15. D. T. Police, “Traffic Statistics and Annual Report,” Government of NCT of Delhi, p. N/A, Various years.
16. F.-Y. Wang, “Parallel Transportation Systems: A Unified Approach for Intelligent Transportation Systems,” IEEE Transactions on Intelligent Transportation Systems, p. 630–638, 2010.
17. A. Bochkovskiy, C.-Y. Wang and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, p. 1–17, 2020.
18. A. Ghosh, “Smart Cities in India — Vision, Challenges and Implications,” Government Policy Report, p. 1–25, 2020.
19. R. K. Bansal and N. K. Gupta, “AI-Based Traffic Management for Indian Smart Cities,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), p. 1231–1235, 2019.