Deep Learning Driven Instinctive Surveillance

Authors

  • Sunil Bhutada Professor, Department of Information Technology, Sreenidhi Institute of Science of Technology, Telangana, India
  • P. Srija Student, Department of Information Technology, Sreenidhi Institute of Science of Technology, Telangana, India
  • S. Sushanth Student, Department of Information Technology, Sreenidhi Institute of Science of Technology, Telangana, India
  • A. Shireesha Student, Department of Information Technology, Sreenidhi Institute of Science of Technology, Telangana, India

DOI:

https://doi.org/10.51983/ajeat-2023.12.1.3636

Keywords:

Surveillance, Deep Learning, Spatio Temporal, Euclidean Distance, Auto-Encoder

Abstract

It is a very boring and laborious job providing observation security. In order to determine whether the exercises that were caught were unusual or suspicious, a labour force is needed. Here, we’ll put together a structure to automate the task of reviewing video reconnaissance. We will regularly review the camera feed to look for any unusual activities like surprising or suspicious ones. and an automatic acknowledgment will be sent to the user with an alert email along with the suspicious frames and SMS to mobile number.  Deep learning computations for deep reconnaissance have improved from earlier encounters. These developments have revealed a key pattern in thorough reconnaissance and promise a significant increase in efficacy. Deep observation is typically used for things like identifying evidence of burglary, finding violence, and recognising explosion potential. We will propose a spatio-temporal auto-encoder for this project that relies on a 3D convolutional brain structure. The decoder then reproduces the edges after the encoder section has removed the spatial and transient data. By recording the recreation misfortune using the Euclidean distance between the original and replicated batch, the odd occurrences are distinguished.

References

G. F. Shidik, E. Noersasongko, A. Nugraha, P. Andono, J. Juanto, and E. J. Kusuma, "A Systematic Review of Intelligence Video Surveillance: Trends, Techniques, Frameworks, and Datasets," IEEE ACCESS, vol. 7, Dec. 2019.

A. B. Nassif, M. A. Talib, Q. Nasir, and F. M. Dhakalbab, "Machine Learning for Anomaly Detection: A Systematic Review," IEEE ACCESS, vol. 9, June 2021.

W. Sultani, C. Chen, and M. Shah, "Real-world Anomaly Detection in Surveillance Videos," Cornell university papers, Feb. 2019.

A. A. Sodemann, M. P. Ross, and B. J. Borghetti, "A Review of Anomaly Detection in Automated Surveillance," IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 42, no. 6, Nov. 2012.

M. Cheng, K. Cai, M. Li, "RWF-2000: An Open Large Scale Video Database for Violence Detection," Slack, Nov. 2019.

S. Ojha and S. Sakhare, "Image processing techniques for object tracking in video surveillance-A survey," in International Conference on Pervasive Computing (ICPC), IEEE, 2015.

[Online]. Available: https://cloud.google.com/tpu/docs/inception-v3-advanced.

Downloads

Published

19-05-2023

How to Cite

Bhutada, S., Srija, P., Sushanth, S., & Shireesha, A. (2023). Deep Learning Driven Instinctive Surveillance. Asian Journal of Engineering and Applied Technology, 12(1), 40–44. https://doi.org/10.51983/ajeat-2023.12.1.3636