Abnormal Activity Recognition in Private Places Using Deep Learning

Authors

  • Anjali Suthar  M. Tech., Department of Artificial Intelligence, Charutar Vidya Mandal University, Anand, Gujarat, India
  • Prof. Jayandrath Mangrolia  Assistant Professor, Department of Information Technology, Charutar Vidya Mandal University, Anand, Gujarat, India
  • Prof. Ravi Patel  Assistant Professor, Department of Information Technology, Charutar Vidya Mandal University, Anand, Gujarat, India

DOI:

https://doi.org/10.32628/CSEIT228688

Keywords:

YOLOv5, Convolution Neural Network (CNN), Artificial Intelligence, Motion Theory

Abstract

Using computer and machine vision technology, the process of analysing human motion is known as "human activity recognition," or HAR. Anomaly detection in security systems is one of the situations in which human activity recognition is useful. As the demand for security growing, surveillance cameras have been widely installed as the foundation for video analysis. Identifying anomalous behaviour demands strenuous human effort, which is one of the main obstacles in surveillance video analysis. It is necessary to establish video recording in order to automatically catch anomalous activities. Using deep learning methods, our intelligent video surveillance system can identify an anomaly in a video. Real-time detection of the actions is also possible, and these video frames will be afterwards preserved as photographs in the system for the user to examine.The suggested Abnormal Activity Recognition system was created with the goal of identifying and detecting irregularities through a live feed in the banking sector, more specifically in an ATM setting.The initial phase of the study focuses on the application of image deep learning techniques to recognise various items and spot unusual behaviour using ATM monitoring systems.

References

  1. Vikas Tripathi; Hindawi Publishing Corporation, "Robust Abnormal Event Recognition via Motion and Shape," Journal of Electrical and Computer Engineering, pp. 1-11, 2015.
  2. Pushpajit A. Khaire and Praveen Kumar, "RGB+D and deep learning based real time detection of suspicious," Springer; Journal of Real-Time Image Processing, pp. 1-13, 2021.
  3. P. A. Khaire, "RGB+D and deep learning based real time detection of suspicious," Journal of Real-Time Image Processing, pp. 1-13, 21.
  4. C. Shiranthika, "Human Activity Recognition Using CNN & LSTM," IEEE, 2021.
  5. T. S. Bora, "HUMAN SUSPICIOUS ACTIVITY DETECTION SYSTEM USING CNN MODEL FOR VIDEO SURVEILLANCE," IJARIIE, 2021.
  6. R. Vrskova, "A New Approach for Abnormal Human Activities Recognition," Sensor, 2022.
  7. S. Sabbu, "LSTM-Based Neural Network to Recognize Human Activities," Hindawi, pp. 1-8, 2022.
  8. Rajeshwari S, Vismitha G, Sumalatha G and Safura Aliya, “Unusual Event Detection for Enhancing ATM Security,” International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, pp. 1-6, 2021.
  9. J. R. Kwapisz, G. M. Weiss, and S. A. Moore, “Activity recognitionusing cell phone accelerometers,” SIGKDD Explor. Newsl. , vol. 12,no. 2,pp. 74–82,Mar. 2011,doi:10. 1145/1964897. 1964918.
  10. A. Murad and J. -Y. Pyun,“Deep RecurrentNeuralNetworksforHuman Activity Recognition,” Sensors, vol. 17, no. 11, p. 2556, Nov. 2017,doi:10. 3390/s17112556.
  11. P. Kuppusamy and C. Harika, “Human Action Recognition using CNNandLSTM-RNNwithAttentionModel”International Journal odInnovativeTechnologyandExploringEngineering(IJITEE),vol. 8,Issue8,pp. 1639-1643,2019
  12. https://www. analyticsvidhya. com/blog/2022/03/basics-of-cnn-in-deep-learning/
  13. Y. Chen, K. Zhong, J. Zhang, Q. Sun, and X. Zhao, “LSTM NetworksforMobileHumanActivityRecognition,”presentedatthe2016International Conference on Artificial Intelligence: Technologies andApplications,Bangkok,Thailand,2016,doi:10. 2991/icaita-16. 2016. 13.
  14. https://ieeexplore. ieee. org/document/9043972
  15. https://towardsdatascience. com/convolutional-neural-networks-explained-9cc5188c4939
  16. C. Jobanputra,J. Bavishi,andN. Doshi,“HumanActivityRecognition:A Survey,” Procedia Computer Science, vol. 155, pp. 698–703, 2019,doi:10. 1016/j. procs. 2019. 08. 100.
  17. https://deepai. org/publication/evaluating-two-stream-cnn-for-video-classification
  18. https://www. codeproject. com/Articles/1366433/Using-Modified-Inception-V3-CNN-for-Video-Processing
  19. https://www. kaggle. com/datasets/mehantkammakomati/atm-anomaly-video-dataset-atmav
  20. A. Murad and J. -Y. Pyun,“Deep RecurrentNeuralNetworksforHuman Activity Recognition,” Sensors, vol. 17, no. 11, p. 2556, Nov. 2017,doi:10. 3390/s17112556.
  21. T. Zebin, M. Sperrin, N. Peek, and A. J. Casson, “Human activityrecognition from inertial sensor time-series using batch normalizeddeep LSTM recurrent networks,” in 2018 40th Annual InternationalConference of the IEEE Engineering in Medicine and Biology Society(EMBC),Honolulu,HI,Jul. 2018,pp. 1–4,doi:10. 1109/EMBC. 2018. 8513115.
  22. https://github. com/pjreddie/darknet/blob/master/data/coco. names
  23. M. Sabokrou, M. Fathy, M. Hoseini, and R. Klette, “Real-time anomaly detection and localization in crowdedness,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2015.
  24. C. Lu, J. Shi, and J. Jia, “Abnormal event detection at 150 fps in matlab ,” in Proceedings of the IEEEinternational conference on computer vision, 2013.
  25. Lu, S. (2019). Deep learning for object detection in video Journal of Physics Conference Series, 1176.
  26. Simonyan, K. , Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2023-05-30

Issue

Volume 9, Issue 3, May-June-2023

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

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

How to Cite

[1]
Anjali Suthar, Prof. Jayandrath Mangrolia, Prof. Ravi Patel, " Abnormal Activity Recognition in Private Places Using Deep Learning" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 9, Issue 3, pp.321-328, May-June-2023. Available at doi : https://doi.org/10.32628/CSEIT228688