Road accidents are a major cause of death and serious injuries, especially due to delays in accident detection and emergency response. Existing systems mainly depend on manual monitoring through CCTV or information from the public, which can be slow and unreliable. This delay in communication often increases the severity of injuries and loss of life. To overcome this problem, this project proposes an AI-based vehicle accident detection system using surveillance cameras with an IoT-enabled accident alert system. The system uses computer vision and deep learning techniques to monitor live video from surveillance cameras and automatically detect accidents in real time.

In conclusion, the results confirm that the proposed AI- based accident detection system is reliable, efficient, and practical for real-time applications. The discussion highlights its advantages in terms of speed, automation, and accuracy, while also identifying areas for further improvement. This system has strong potential for deployment in smart city infrastructure and intelligent transportation systems to enhance road safety and emergency response mechanisms.

1] S. S. Raut, V. B. Gaikwad, and P. R. Deshmukh, “Accident Detection and Alert System Using IoT,” International Journal of Engineering Research & Technology (IJERT), vol. 8, no. 5, pp. 123–126, 2019. [2]A. Sharma and R. Singh, “Smart Accident Detection and Notification System Using Deep Learning,” IEEE Access, vol. 8, pp. 145123– 145135, 2020. [3]M. Patel and J. Shah, “Real-Time Vehicle Accident Detection Using Image Processing,” International Journal of Computer Applications, vol. 180, no. 7, pp. 20–25, 2018. [4]K. Zhang, Y. Wang, and L. Chen, “Deep Learning-Based Traffic Accident Detection Using Surveillance Cameras,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 10, pp. 4323–4333, 2020. [5]World Health Organization, “Global Status Report on Road Safety,” 2018. [6]National Highway Traffic Safety Administration, “Traffic Safety Facts Annual Report,” 2020. [7]Espressif Systems, “ESP32 Technical Reference Manual,” 2021. [8]Arduino IDE Documentation, “Programming ESP32 for IoT Applications,” 2022. [9]OpenCV Library Documentation, “Image Processing and Object Detection,” 2021. [10]TensorFlow Documentation, “Deep Learning for Image Classification,” 2022.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close