Realtime Automated Incident Detection

Authors

  • Palanivel N
  • Chandramouli M
  • Hariharan R
  • Mohanram R
  • Vittal Devaraju G
  • Preetisha S

Keywords:

Real-Time Incident Detection, CCTV Surveillance, Public Safety, Computer Vision, Machine Learning, Violent Crimes, Accidents, Automated Reporting, Chatbot Integration, Video Data Analysis, Emergency Alerts, Threat Detection, LSTM Networks, Mobile Networks

Abstract

In a rapidly interconnected world, maintaining public safety is paramount. This work introduces a novel approach to utilizing CCTV camera feeds to identify real-time events like accidents and violent offenses. The system continuously analyzes video data by applying advanced computer vision methods and machine learning models, notably combining Long Short-Term Memory (LSTM) networks and Mobile Networks in Convolutional Neural Networks (CNN). Upon detection of an event, the system captures a short video record as evidence and reports it immediately through a chatbot, with ease of contact with the respective authorities. Through the chatbot, real-time alerts are generated, allowing swift action and softening the blow of such incidents. By synergizing automated event detection and real-time reporting, a solid mechanism for increasing public safety and creating a secure community is put into place

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

Gao, Y., Liu, Y., & Zhang, W. (2021). Video anomaly detection with convolutional LSTM network. IEEE Access, 9, 103578–103586.

Kwon, J., & Yoo, S. (2022). Spatio-temporal anomaly detection using a hybrid model of CNN and LSTM for surveillance videos. Journal of Visual Communication and Image Representation, 76, 103149.

Li, B., Lu, S., & Zhang, H. (2021). A hybrid model for anomaly detection in traffic surveillance videos using LSTM and autoencoders. Computers, Environment, and Urban Systems, 87, 101621.

Sayed, H. A., & Wahba, H. (2020). Anomaly detection in surveillance videos using deep learning techniques. International Journal of Computer Applications, 975, 20-25.

Wu, Z., & Xu, Y. (2022). Real-time anomaly detection in surveillance videos using deep learning models. Proceedings of the IEEE/CVF

Winter Conference on Applications of Computer Vision (WACV), 2919–2928.

Kumar, V., & Singh, R. (2020). Spatiotemporal anomaly detection using CNN-LSTM for surveillance videos. Proceedings of the IEEE International Conference on Multimedia & Expo (ICME), 234–239.

Basharat, A., & Azhar, F. (2020). Video anomaly detection using LSTM networks with self-attention mechanism. Neurocomputing, 400, 279-289.

Yang, S., & Li, X. (2021). Temporal-spatial anomaly detection in CCTV video using CNN and LSTM networks. Journal of Visual Communication and Image Representation, 79, 103250.

Zhang, L., & Chen, Z. (2022). Deep learning for anomaly detection in surveillance video: A survey. IEEE Access, 10, 112388–112406

Downloads

Published

2025-05-26

How to Cite

1.
N P, M C, R H, R M, G VD, S P. Realtime Automated Incident Detection. J Neonatal Surg [Internet]. 2025May26 [cited 2025Sep.21];14(28S):74-83. Available from: https://www.jneonatalsurg.com/index.php/jns/article/view/6563

Issue

Vol. 14 No. 28S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.