Real-Time Pedestrian Detection and Passive Signal Monitoring Using YOLOv12
DOI:
https://doi.org/10.56532/mjsat.v6iS2.808Keywords:
Pedestrian Crossing, Image Processing, Image Detection and CountingAbstract
Pedestrian crossings are vital for urban safety and traffic management. However, fixed-time signal controls ignore real-time pedestrian demand, leading to inefficient traffic flow and underutilized infrastructure. To address this, this project introduces a Real-Time Pedestrian Detection and Passive Signal Monitoring Using YOLOv12. The core objectives were to develop a pedestrian detection and counting system, implement analytics functionalities, and evaluate overall performance using recorded footage. The proposed system was validated using real-world video and publicly available datasets. Experimental results demonstrated that the system successfully performs real-time pedestrian counting, demand classification, and adaptive traffic light control. Notably, the adaptive control strategy optimized traffic flow by dynamically reducing the pedestrian green-light duration from 8 seconds to 4 seconds when no active crossing demand was detected. This intelligent adjustment resulted in a cumulative time savings of approximately 2.15 minutes across 26 crossing cycles. The successful development of this system highlights the immense capability of integrating computer vision and deep learning for pedestrian monitoring and analytics applications.
References
A. Sakurai, N. Kajio, and K. Yamamoto, “ShibuyaSocial: Multi-scale model of pedestrian flows in scramble crossing,” arXiv, art. no. 2512.18550, Dec. 2025, doi: https://doi.org/10.48550/arXiv.2512.18550.
“Bukit Bintang set for glow-up to rival Tokyo’s Ginza and Singapore’s Orchard Road, says housing minister.” Accessed: Dec. 11, 2025. url: https://www.msn.com/en-my/news/national/bukit-bintang-set-for-glow-up-to-rival-tokyo-s-ginza-and-singapore-s-orchard-road-says-housing-minister/ar-AA1PoMRk.
M. Patel and H. Elgazzar, “Pedestrian Crosswalk Safety at Intersections using YOLOv8 Detection,” 2024 IEEE 15th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 426–430. doi: https://doi.org/10.1109/UEMCON62879.2024.10754669.
Samuel Omefe, “Assessment of the effectiveness of adaptive traffic signal control systems in reducing pedestrian-vehicle conflicts at high-risk crossings,” GSC Advanced Research and Reviews, vol. 24, no. 1, pp. 140–153, Jul. 2025, doi: https://doi.org/10.30574/gscarr.2025.24.1.0191.
M. Pomoni, “Smart Crosswalks for Advancing Road Safety in Urban Roads: Conceptualization and Evidence-Based Insights from Greek Incident Records,” Future Transportation, vol. 5, no. 4, Dec. 2025, doi: https://doi.org/10.3390/futuretransp5040180.
S. Minaee, Y. Boykov, F. Porikli, A. Plaza, N. Kehtarnavaz, and D. Terzopoulos, “Image Segmentation Using Deep Learning: A Survey,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 7, pp. 3523–3542, Jul. 2022, doi: https://doi.org/10.1109/TPAMI.2021.3059968.
C. Ashwini, S. Sharma, A. Srivastava, and S. Sinha, “To identify and recognize the object for traffic analysis system using deep learning,” International Journal of Innovative Technology and Exploring Engineering, vol. 8, no. 12, pp. 1621–1624, Oct. 2019, doi: https://doi.org/10.35940/ijitee.L3155.1081219.
C. Li and Y. Sun, “Enhancing Pedestrian Detection Algorithm Based on YOLOv3-ES Network,” Proceedings - 2023 International Conference on Image Processing and Computer Vision, IPCV 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 118–122. doi: https://doi.org/10.1109/IPCV57033.2023.00029.
X. Wang, R. Wei, and R. Zou, “Research on Pedestrian Detection Algorithm Based on Improved YOLOv5,” 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 1109–1112. doi: https://doi.org/10.1109/EIECS59936.2023.10435608.
Y. Yue, X. Kong, R. Pan, and W. Shan, “Research on Intelligent Traffic Pedestrian Detection Algorithm Based on Improved YOLOv8,” 2024 5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 384–388. doi: https://doi.org/10.1109/ICAICE63571.2024.10864271.
X. Li and L. Ma, “DED-YOLOv8:Dense pedestrian detection algorithm based on YOLOv8,” 2024 4th International Symposium on Computer Technology and Information Science, ISCTIS 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 545–548. doi: https://doi.org/10.1109/ISCTIS63324.2024.10699141.
J. Mao, H. Wang, and D. Li, “Optimized and Improved YOLOv8 Dense Pedestrian Detection Algorithm,” Proceedings - 2024 9th International Conference on Communication, Image and Signal Processing, CCISP 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: https://doi.org/10.1109/CCISP63826.2024.10765506.
C. Hu, Y. Wei, and X. Tao, “Lightweight YOLOv8 Pedestrian Detection Model Based on FasterNet,” 2024 4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 787–790. doi: https://doi.org/10.1109/AIIM64537.2024.10934361.
Li, W. Leong, and H. Zhang, “YOLOv10-Based Real-Time Pedestrian Detection for Autonomous Vehicles,” 2024 IEEE 8th International Conference on Signal and Image Processing Applications, ICSIPA 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: https://doi.org/10.1109/ICSIPA62061.2024.10686546.
M. Hasan, M. K. M. Rabby, I. Jahan, M. J. A. Soeb, and M. F. Jubayer, "The Evolution and Advancement of YOLO Algorithms in Object Detection: From Real-Time Breakthroughs to Modern Architectures," Preprints.org, Oct. 2025, doi: https://doi.org/10.20944/preprints202510.2019.v1.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mohd Nur Aiman Sulaiman, Nik Shahidah Afifi Md Taujuddin, Suhaila Sari, Ahmad Raqib Ab Ghani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
