Authors : Darshan Shinde; Sanket Patil; Shreyas Patil; Abhinandan Kavathekar; Vaibhav Magdum

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/42ds8mxu

Scribd : https://tinyurl.com/333xajt3

DOI : https://doi.org/10.38124/ijisrt/26May1720

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

Abstract : Road accidents are one of the leading causes of fatalities in India, with the Ministry of Road Transport and Highways (MoRTH) recording over 4.8 lakh accidents in 2023, resulting in 1.72 lakh deaths. A major contributing factor is the delay in accident detection and emergency response. This paper presents a real-time Accident Detection and Alert System that integrates YOLOv8 object detection, OpenCV-based video stream processing, Twilio API for SMS-based alert delivery, annotated snapshot archiving, and structured rotating log management into a single deployable pipeline. The system captures video from surveillance cameras, dashcams, or RTSP streams, runs per-frame inference using a customtrained YOLOv8 model with a confidence threshold of 0.6, and upon detecting an accident, immediately saves an annotated snapshot, dispatches an SMS alert containing the detection timestamp and snapshot path, and logs the event with full metadata. Alert throttling of 30 seconds prevents notification spam for prolonged events. Early testing demonstrates reliable detection with minimal false positives, SMS delivery within 1–2 seconds of detection, and structured per-frame logging suitable for post-incident review. The system is designed to reduce dependency on manual reporting, target emergency response within the medical “golden hour,” and deploy on existing CCTV infrastructure without requiring in-vehicle hardware modifications.

Keywords : Accident Detection, YOLOv8, Computer Vision, Real-Time Monitoring, Alert System, Road Safety, Twilio API, OpenCV, Deep Learning.

References :

1. Ministry of Road Transport and Highways, “Road Accidents in India 2023,” Government of India, New Delhi, 2023.
2. World Health Organization, “Global Status Report on Road Safety 2023,” WHO Press, Geneva, 2023.
3. Ultralytics, “YOLOv8 Documentation,” 2023. [Online]. Available: https://docs.ultralytics.com/
4. Twilio, “Twilio Messaging API Documentation,” 2023. [Online]. Available: https://www.twilio.com/docs/sms
5. OpenCV, “OpenCV Documentation,” 2023. [Online]. Available: https://opencv.org/
6. A. Chaurasiya et al., “Accident Detection using YOLOv11 with Spatio-Temporal Feature Fusion,” International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 09, no. 05, May 2025. ISSN: 2582-3930.
7. H. A. Ali, S. Nassar, and H. Al-Tuwaijari, “Vehicle Accident Detection and Notification System using CNN-SVM,” Iraqi Journal of Science, 2024.
8. S. Singh et al., “Real-Time Accident Detection using YOLOv5 and Random Forest,” IEEE Xplore, 2023.
9. W. Sultani, C. Chen, and M. Shah, “Real-world Anomaly Detection in Surveillance Videos,” in Proc. IEEE/CVF CVPR, 2018.
10. W. Liu et al., “SSD: Single Shot MultiBox Detector,” in Proc. ECCV, 2016, pp. 21–37.
11. R. Mitra, R. D. Singh, V. K. Jain, and S. Manohar, “Accident Detection Using YOLO,” International Journal of Advanced Research in Computer Science, vol. 11, no. 6, Jun. 2023. ISSN: 2320-2882.
12. M. I. B. Ahmed et al., “A Real-Time Computer Vision-based Approach to Detection and Classification of Traffic Incidents,” Big Data and Cognitive Computing, vol. 7, no. 22, 2023.
13. Y. Zhou, “Vehicle Image Recognition using Deep Convolution Neural Network and Compressed Dictionary Learning,” Journal of Information Processing Systems, vol. 17, pp. 411–425, 2021.
14. A. Kumar and P. Shukla, “Real-Time Road Accident Detection using YOLO and OpenCV,” arXiv preprint arXiv:2106.05913, Jun. 2021.
15. S. Ghosh, “Automatic Car Crash Detection Using CNNs,” IEEE Transactions on Intelligent Transportation Systems, 2019.
16. L. K. Wani, M. M. Momin, S. Bhosale, A. Yadav, and M. Nili, “Vehicle Crash Detection using YOLO Algorithm,” International Journal of Innovative Research in Computer Science & Technology, 2022.