Online Registration

ISO 9001:2015

INTERNATIONAL JOURNAL OF GLOBAL RESEARCH INNOVATIONS & TECHNOLOGY (IJGRIT) [ Vol. 4 | No. 2 | April - June, 2026 ]

An Edge-Based System and Method for Real-Time Detection and Reporting of Highway Road Accidents

Mrs. Sneha D. Patil, Mr. Karansing G. Patil, Mr. Amit G. Kasbe, Miss. Aadesh C. More & Mr. Lalit S. Patil

Highway accidents remain a significant safety concern due to high travel speeds and delays in emergency response. Fast and dependable detection is essential to reduce injuries and prevent additional damage. This work presents a real-time accident monitoring approach that performs analysis directly on embedded edge devices. By processing data locally rather than relying on continuous cloud connectivity, the system achieves quicker response and reliable operation under varying network conditions. The method integrates deep learning–based visual analysis with motion evaluation across successive video frames to identify potential collision events. To improve reliability and minimize false alerts, detections are confirmed across multiple frames before final classification. Once verified, the system automatically sends an alert containing location details, time information, and relevant context through a 4G communication link to support prompt emergency response. Testing on embedded platforms shows that the system maintains an effective balance between computational efficiency and detection performance. Overall, the design provides a scalable and cost-efficient solution for enhancing highway safety through continuous real-time monitoring.

  1. World Health Organization, “Global Status Report on Road Safety,” WHO Press, Geneva, 2018.
  2. National Highway Traffic Safety Administration, “Traffic Safety Facts,” U.S. Department of Transportation, 2020.
  3. R. Bhandari and S. Kumar, “Sensor-Based Accident Detection Systems: A Review,” IJERT, vol. 6, no. 5, pp. 112–118, 2017.
  4. M. Abdelwahab and A. Abdelgawad, “Accident Detection and Reporting Using GPS and GSM,” IJCSMC, vol. 3, no. 4, pp. 620–630, 2014.
  5. N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” CVPR, pp. 886–893, 2005.
  6. J. Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection,” CVPR, pp. 779–788, 2016.
  7. J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv:1804.02767, 2018.
  8. Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, pp. 436–444, 2015.
  9. S. Ren et al., “Faster R-CNN: Towards Real-Time Object Detection,” IEEE TPAMI, vol. 39, no. 6, 2017. [10]W. Liu et al., “SSD: Single Shot MultiBox Detector,” ECCV, pp. 21–37, 2016.
  10. P. Zhang et al., “Anomaly Detection in Video Surveillance: A Review,” IEEE Access, vol. 6, pp. 50732– 50746, 2018.
  11. A. Doshi and M. Trivedi, “On the Roles of Eye Gaze and Head Dynamics in Predicting Driver’s Intent,” IEEE T-ITS, vol. 10, no. 3, 2009.
  12. M. Satyanarayanan, “The Emergence of Edge Computing,” IEEE Computer, vol. 50, no. 1, pp. 30–39, 2017.
  13. S. Shi, Q. Wang, and P. Chu, “Edge Computing: Vision and Challenges,” IEEE IoT Journal, vol. 3, no. 5, 2016.
  14. X. Xu et al., “Edge Intelligence: Architectures, Challenges, and Applications,” IEEE Communications Magazine, vol. 57, no. 5, 2019.
  15. H. Wang et al., “Video-Based Traffic Accident Detection,” IEEE T-ITS, vol. 18, no. 7, 2017.
  16. A. Jain and C. Kanhere, “Anomaly Detection in Road Traffic Videos,” IEEE ITS Conference, 2018.
  17. S. Gupta et al., “Real-Time Accident Detection Using Embedded Systems,” IJARCSSE, vol. 7, no. 3, 2017.
  18. T. Chen et al., “Deep Learning for Intelligent Transportation Systems,” IEEE T-ITS, vol. 21, no. 9, 2020.
  19. R. Roman et al., “Features and Challenges of the Internet of Things,” Computer Networks, vol. 57, no. 10, 2013.
  20. K. Ashton, “That ‘Internet of Things’ Thing,” RFID Journal, 2009.

DOI:

Article DOI:

DOI URL:

Download Full Paper:

Download