International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Real-Time Tunnel Accident Detection and Tracking Using YOLOv5 |
|---|---|
| ABSTRACT | Real-Time Tunnel Accident Detection and Tracking Using YOLOv5 is an intelligent traffic monitoring system designed to automatically detect vehicle collisions in tunnel environments using computer vision and deep learning techniques. Traditional tunnel monitoring depends on continuous human observation, which may lead to delayed responses and missed incidents. To overcome this limitation, the system uses the YOLOv5 object detection model to identify vehicles in each frame of recorded tunnel traffic videos. The detected vehicles are then tracked using the DeepSORT tracking algorithm, which assigns unique IDs and follows each vehicle across frames. The tracking information such as frame number, object ID, and bounding box coordinates is stored for further analysis. A collision detection module analyzes vehicle interactions by calculating distance, velocity, and overlap between bounding boxes to determine possible accidents. When a collision is detected, the system highlights it in the output video and records the accident details in a log file. This automated approach reduces manual monitoring and improves traffic safety by identifying accidents efficiently. The final output includes a processed video showing detected collisions along with stored accident information for future analysis. |
| AUTHOR | KADAMANCHI REVATHI, G.NAGA SUJINI, DR.V.SUBBARAMAIAH, DR.K. RAJITHA Student, Department of Computer Science and Engineering, Mahatma Gandhi Institute of Technology, Gandipet, India Assistant Professor, Department of Computer Science and Engineering, Mahatma Gandhi Institute of Technology, Gandipet, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404108 |
| pdf/108_Real-Time Tunnel Accident Detection and Tracking Using YOLOv5.pdf | |
| KEYWORDS | |
| References | 1. F. Hamami, I. Darmawan et al., "Optimizing Traffic Safety: YOLOv11 and DeepSORT for Speed Detection and Safe Distance Monitoring," IEEE, 2025, DOI: 10.1109/ICERA66156.2025.11087337. 2. E. Elakiya, A. Singh et al., "AI-Powered Road Safety: A Unified YOLO Network for Real-Time Helmet Detection, Speed Estimation and Number Plate Recognition," IEEE, 2025, DOI: 10.1109/ICIRCA65293.2025.11089859. 3. S. Subramani V, V. Kumar S et al., "Smart Tunnel Traffic Control System using IoT and Machine Learning," IEEE, 2025, DOI: 10.1109/ICVADV63329.2025.10961894. 4. R. Devi S. M. et al., "A Real-Time Multiple Traffic Violation Detection System Using DeepSORT," IEEE, 2024, DOI: 10.1109/AISP61711.2024.10870840. 5. P. Phiphimai, S. Tantrairatn et al., "Enhancing Safety and Efficiency with Autonomous Navigation Systems: Integrating Real-Time Object Detection, Tracking, and Trajectory Prediction," IEEE, 2024, DOI: 10.1109/KST61284.2024.10499659. 6. B. Ding, "Design and Development of Intelligent Lighting Control System for Urban Tunnel," IEEE, 2024, DOI: 10.1109/EI264398.2024.10990847. 7. J. Li et al., "WiFi Sensing Based Fire Detection System for Vehicular Tunnels," IEEE, 2024, DOI: 10.1109/GLOBECOM52923.2024.10901736. 8. Q. Liu et al., "System Design and Research on Traffic Tunnel Inspection System Based on Computer Vision and Audition," IEEE, 2024, DOI: 10.1109/BMSB62888.2024.10608342. |
