ALERTEYE: REAL-TIME AI-DRIVEN INCIDENT DETECTION USING YOLOV11 AND GNN MODEL
The increasing complexity of urban environments presents significant challenges for public safety, particularly regarding the delayed detection of road accidents and fire outbreaks. Conventional surveillance systems are primarily reactive and rely on continuous human monitoring, which is prone to fatigue and error. This paper presents "AlertEye," an automated real-time detection and emergency notification system. By leveraging the YOLOv11 deep learning architecture, the system achieves high-speed object detection from live camera feeds. When a hazard is identified with high confidence, a Flask-based backend utilizes Firebase Cloud Messaging (FCM) to deliver instantaneous push notifications to a mobile application. Experimental results demonstrate that the system significantly reduces response latency, offering a proactive solution for emergency intervention.
Singh, S., Gaikwad, M., Shinde, S., Shewale, T. & Sangit, P. (2026). AlertEye: Real-time AI-Driven Incident Detection using Yolov11 and GNN Model. International Journal of Science, Strategic Management and Technology, 02(04). https://doi.org/10.55041/ijsmt.v2i4.312
Singh, Shashank, et al.. "AlertEye: Real-time AI-Driven Incident Detection using Yolov11 and GNN Model." International Journal of Science, Strategic Management and Technology, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i4.312.
Singh, Shashank,Mayuresh Gaikwad,Sujal Shinde,Tanvi Shewale, and Pranita Sangit. "AlertEye: Real-time AI-Driven Incident Detection using Yolov11 and GNN Model." International Journal of Science, Strategic Management and Technology 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i4.312.
2.Available: https://doi.org/10.48550/arXiv.2410.17725
3.A. Mokar, S. O. Fageeri, and S. E. Fattoh, "Using Firebase Cloud Messaging to Control Mobile Applications," in 2019 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), Khartoum, Sudan, 2019, pp. 1-5. doi: 10.1109/ICCCEEE46830.2019.9071008.
4.H. Alshareef, A. M. Yousef, L. A. Bubaker, and T.
5.Tofek, "Real-Time Fire Detection Using YOLOv8 and Twilio SMS Alerts," Libyan Journal of Medical and Applied Sciences (LJMAS), vol. 3, no. 4, pp. 90-99, Nov. 2025. doi: 10.64943/ljmas.v3i4.221.
6.Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788.
7.Ultralytics, "YOLOv11 Documentation and Pre-trained Models," 2024. [Online]. Available: https:// com/ultralytics/ultralytics (Accessed: Mar. 23, 2026).
8.Twilio Inc., "Twilio Programmable SMS API Reference," [Online]. Available: https:// www.twilio.com/docs/sms (Accessed: Mar. 23, 2026).
9.Firebase, "FCM Architectural Overview," Google Developers, [Online]. Available: https://
10.firebase.google.com/docs/cloud-messaging (Accessed: Mar. 23, 2026).