Theft Detection in Surveillance Videos Using Mobilenetv2 a Deep Learning Approach for Binary Classification

DOI

10.2991/978-94-6463-718-2_89How to use a DOI?

Keywords

MobileNetV2; theft detection; surveillance videos; deep learning; real-time detection; binary classification; anomaly detection; action recognition; low-resolution videos; real-time feedback; computational efficiency; scalable systems; human activity recognition; false positive reduction; large-scale surveillance

Abstract

Many modern convolutional neural network architectures have been introduced, including MobileNetV2, which are both optimized for mobile/edge performance and suitable for theft detection on surveillance video. Due to the lightness of MobileNetV2, the proposed system allows the detection and classification of theft-related activities in real-time and in complex or crowded environments. It requires minimal computation and enables deployments at scale throughout expansive surveillance networks. The balance allows the model to generalize across lighting scenarios, low-res videos and dynamic human behaviors, ensuring practical application effectiveness. In addition, it detects low-key behaviors of theft, and generalizes to unseen thefts, offering a solution for ongoing monitoring of its security. It reduces false positives, lessens computational burden, and provides immediate feedback for on-the-spot intervention, therefore making it an ideal solution for large-scale surveillance systems for public and private places.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - V. Sharmila
AU  - M. Venkatesan
AU  - R. Keerthana
AU  - S. Gokul
AU  - K. Karthikkumar
AU  - T. G. B. Krishna Suthers Raj
PY  - 2025
DA  - 2025/05/23
TI  - Theft Detection in Surveillance Videos Using Mobilenetv2 a Deep Learning Approach for Binary Classification
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1059
EP  - 1072
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_89
DO  - 10.2991/978-94-6463-718-2_89
ID  - Sharmila2025
ER  -