International Journal of Electronics and Computer Applications

Volume: 2 Issue: 1

  • Open Access
  • Original Article

Anomaly Detection in Videos Using Deep Learning

Ashwini Patil1∗

1Assistant Professor, Department of E&TC, Ajeenkya D Y Patil School of Engineering, Pune,
Maharashtra, India

 

Year: 2025, Page: 90-96, Doi: https://doi.org/10.70968/ijeaca.v2i1.D1004

Received: Jan. 25, 2025 Accepted: May 10, 2025 Published: June 28, 2025

Abstract

In recent decades, surveillance cameras have been widely deployed in various locations for security and monitoring. The video data analysis captured by these cameras plays a crucial role in event prediction, real-time tracking, and goal-driven applications such as anomaly and intrusion detection. With advancements in Artificial Intelligence (AI), deep learning-based approaches, particularly Convolutional Neural Networks (CNNs), have significantly improved anomaly detection accuracy. This study proposes a novel deep-learning framework for detecting anomalies in video surveillance, leveraging CNNs for spatial feature extraction. In recent decades, surveillance cameras have been widely deployed in various locations for security and monitoring. The video data analysis captured by these cameras plays a crucial role in event prediction, real-time tracking, and goal-driven applications such as anomaly and intrusion detection. With advancements in Artificial Intelligence (AI), deep learning-based approaches, particularly Convolutional Neural Networks (CNNs), have significantly improved anomaly detection accuracy. This study proposes a novel deep-learning framework for detecting anomalies in video surveillance, leveraging CNNs for spatial feature extraction. The approach is inspired by previous studies, such as "Anomaly Detection in Surveillance Videos Using Deep Learning" 1, which demonstrated high efficiency in recognizing abnormal patterns. The UCSD dataset has been used to assess the suggested approach, showing improved accuracy in anomaly detection compared to existing methods. The findings highlight the potential of deep learning in enhancing automated surveillance systems, contributing to intelligent security monitoring and public safety. 1

Keywords: Anomaly Detection in Videos Using Deep Learning

References

  1. Nithesh K, Tabassum N, Geetha DD, Kumari RDA. Anomaly Detection in Surveillance Videos Using Deep Learning. In: 2022 International Conference on Knowledge Engineering and Communication Systems (ICKES). (pp. 1-6) IEEE. 2023.

  2. Chandrakala S, Deepak K. A Review of Deep Learning-Based Anomaly Detection Strategies in VideosIEEE Access. 2023;11:123456–123478.

  3. Wang B, Yang C. Video Anomaly Detection Based on Convolutional Recurrent AutoEncoderSensors. 2022;22(12):4647. Available from: https://dx.doi.org/10.3390/s22124647

  4. Sun F, Zhang J, Wu X, Zheng Z, Yang X. Video Anomaly Detection Based on Global–Local Convolutional AutoencoderElectronics. 2024;13(22):4415. Available from: https://dx.doi.org/10.3390/electronics13224415

  5. Duong HT, Le VT, Hoang VT. Deep Learning-Based Anomaly Detection in Video Surveillance: A SurveySensors. 2023;23(11):5024. Available from: https://dx.doi.org/10.3390/s23115024

  6. Zhao M, Liu Y, Liu J, Zeng X. Exploiting Spatial-temporal Correlations for Video Anomaly DetectionarXiv preprint . 2022;p. 1–7. Available from: https://arxiv.org/pdf/2211.00829

  7. Wu C, Shao S, Tunc C, Satam P, Hariri S. An explainable and efficient deep learning framework for video anomaly detectionCluster Computing. 2022;25(4):2715–2737. Available from: https://dx.doi.org/10.1007/s10586-021-03439-5

  8. Zeng X, Jiang Y, Ding W, Li H, Hao Y, Qiu Z. A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in VideosIEEE Transactions on Circuits and Systems for Video Technology. 2023;33(1):200–212. Available from: https://dx.doi.org/10.1109/tcsvt.2021.3134410

  9. Matei A, Glavan A, Talavera E. Deep Learning for Scene Recognition from Visual Data: A Survey. In: International Conference on Hybrid Artificial Intelligence Systems, Lecture Notes in Computer Science. (Vol. 12344, pp. 763-773) 2020.

  10. FE, Cassie E, Nguyen HPT, et al. Anomaly Detection for Sensor Signals Utilizing Deep Learning Autoencoder-Based Neural NetworksBioengineering . 2023;10(4):405. Available from: https://doi.org/10.3390/bioengineering10040405

  11. Ma H, Zhang L. Attention-based framework for weakly supervised video anomaly detectionThe Journal of Supercomputing. 2022;78(6):8409–8429. Available from: https://dx.doi.org/10.1007/s11227-021-04190-9

  12. Ouyang Y, Shen G, Sanchez V. Look at Adjacent Frames: Video Anomaly Detection Without Offline Training. In: Computer Vision – ECCV 2022 Workshops, Lecture Notes in Computer Science . (Vol. 13859, pp. 642-658) 2023.

  13. Dilek E, Dener M. Computer Vision Applications in Intelligent Transportation Systems: A SurveySensors. 2023;23(6):2938. Available from: https://dx.doi.org/10.3390/s23062938

  14. Xia X, Gao Y. Video Abnormal Event Detection Based on One‐Class Neural NetworkComputational Intelligence and Neuroscience. 2021;2021(1). Available from: https://dx.doi.org/10.1155/2021/1955116

  15. Hojjati H, Armanfard N. DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly DetectionIEEE Transactions on Knowledge and Data Engineering. 2024;36(8):3739 –3750. Available from: https://dx.doi.org/10.1109/tkde.2023.3328882

Cite this article

Patil A. (2025). Anomaly Detection in Videos Using Deep Learning. International Journal of Electronics and Computer Applications. 2(1): 90-96. https://doi.org/10.70968/ijeaca.v2i1.D1004

Views
74
Downloads
36
Citations