Volume 2 Issue 4 | 2025 | View PDF
Paper Id:IJMSM-V2I4P122
doi: 10.71141/30485037/V2I4P122

Smart Road Safety System Using YOLO-Based Object Detection and IoT Communication in Mountainous Terrains

R. Mahalakshmi, R. Bhavithra, K. Prabavathi, B. Navalakshmi

Citation:
R. Mahalakshmi, R. Bhavithra, K. Prabavathi, B. Navalakshmi, "Smart Road Safety System Using YOLO-Based Object Detection and IoT Communication in Mountainous Terrains" International Journal of Multidisciplinary on Science and Management, Vol. 2, No. 4, pp. 207-214, 2025.

Abstract:
Road grid lock in this high-speed world is a serious big issue due to road accidents and incorrect traffic lights. It is bad particularly in hilly areas, where poor visibility and tight turns make it even worse to have an accident. The proposed system offers an IoT-ambivalent prototype that should be introduced to improve safety on the roads in mountainous areas, and it should involve real-time object detection and alert signaling. The live video streams of the road conditions are recorded on two cameras, and the YOLO (You Only Look Once) model is used to process them to identify vehicles precisely and quickly. The processed data is stored and controlled on the Firebase real-time database that promises efficient data processing and communication. The Node MCU microcontroller is used to access the data that Firebase detects to turn on a pole-mounted red light to warn oncoming traffic about possible dangers. A solution to reducing accidents in dangerous hilly environments is to utilize the proposed architecture, which integrates YOLO-based detection and IoT-based communication with secure data transmission to provide a reliable and responsive solution to the problem.

Keywords: Road Safety, Accident Detection, Intelligent Transportation System, Emergency Response, IoT Communication, Real-time Monitoring.

References:
1. G. Vanita, A. Ramakant, S. Dalve, A. Rapatwar, and S. Dhage, “Accident Prevention System using IR Sensors,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), vol. 6, no. 2, pp. 203–207, Apr. 2020.
2. S. Nanda, H. Joshi, and S. Khairnar, “IoT-Based Intelligent Framework for Accident Detection and Prevention,” in Proc. 4th Int. Conf. on Computing Communication Control and Automation (ICCUBEA), Pune, India, 2018, pp. 1–6.
3. K. S. Murugan and R. Roshni, “Smart Accident Detection and Prevention Mechanism for Four-Wheeler Vehicles,” in Proc. 6th Int. Conf. on Communication and Electronics Systems (ICCES), Coimbatore, India, 2021, pp. 1590–1593.
4. S. Gowtham, S. Sethumathavan, and M. Sutharshan, “Real Time Embedded System for Accident Prevention,” International Journal of Engineering Research & Technology (IJERT), vol. 9, no. 2, Feb. 2020.
5. A. John, and P. R. Nishanth, “Real Time Embedded System for Accident Prevention,” in Proc. Int. Conf. on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India, 2017, pp. 645–648.
6. S. Thokala, R. Jakkani, M. Alli, and H. Shanmugasundaram, “Machine Learning-Enabled System for Accident Prediction and Prevention,” in Proc. Int. Conf. on Computer Communication and Informatics (ICCCI), Coimbatore, India, 2023, pp. 1–6.
7. I. Ashraf, S. Hur, G. Kim, and Y. Park, “Analyzing Performance of YOLOx for Detecting Vehicles in Bad Weather Conditions,” Sensors, vol. 24, 2024.
8. R. Chandana and A. Ramachandra, “Comparative Study of Real-Time Object Detection Using YOLO and CNN Architectures,” arXiv preprint, arXiv:2208.00773, 2022.
9. T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object Detection Using YOLO: Challenges, Architectural Successors, Datasets and Applications,” Multimedia Tools and Applications, vol. 82, pp. 9243–9275, 2023.
10. J. Du, “Analysis of CNN and YOLO-Based Approaches for Object Detection,” Journal of Physics: Conference Series, vol. 1004, p. 012029, 2018.
11. Z.-Q. Zhao, P. Zheng, S.-T. Xu, and X. Wu, “Deep Learning Approaches for Object Detection: A Comprehensive Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, pp. 3212–3232, 2019.
12. S. Devi, K. Thopalli, P. Malarvezhi, and J. J. Thiagarajan, “Enhancing Single-Stage Detectors for Pedestrian Recognition in Low-Light Scenarios,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 36, no. 22, p. 2250034, 2022.
13. Z. Jiang, L. Zhao, S. Li, and Y. Jia, “Improved YOLOv4-Tiny for Efficient Real-Time Object Detection,” arXiv preprint, arXiv:2011.04244, 2020.
14. R. Li, X. Zeng, S. Yang, Q. Li, A. Yan, and D. Li, “ABYOLOv4: Enhanced Multi-Scale Human Detection Using Improved YOLOv4,” EURASIP Journal on Advances in Signal Processing, 2024.
15. C. Gao, Q. Zhang, Z. Tan, G. Zhao, S. Gao, E. Kim, and T. Shen, “Applying Optimized YOLOv8 for Heritage Conservation: Enhanced Object Detection in Jiangnan Traditional Private Gardens,” Heritage Science, vol. 12, p. 31, 2024.