Skip to main content
Springer Nature Link
Log in

Automatic and multimodal nuisance activity detection inside ATM cabins in real time

  • 1215: Multimodal Interaction and IoT Applications
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Automated teller machine (ATM) has changed the banking system for almost everyone, but it also invites security threats in form of personals for making nuisance with either genuine ATM users or ATM itself. In the pandemic scenario, when financial crunch is spanned around, more vigilance is required for ATMs. Though CCTV is available in almost all ATMs but manual monitoring of CCTV footage of ATM cabin is not sufficient to detect nuisance in real time. So there is a need for real time nuisance detector which could reduce nuisance activities inside ATM cabins. The detection of nuisance through generic camera is a challenging task due to multimodal nature of activities. For example interacting with ATM at your wish is a normal activity while somebody force you for ATM interaction in ATM cabin, is nuisance or abnormal activity. In this paper, a multimodal, computationally economical but efficient method is proposed for real time nuisance detection. In a CCTV stream, region wise local motions have been captured through motion projection matrix and local motion histograms to extract features. Further for classification, a tree bagger model has been used. Classification accuracy for proposed method on ATM dataset has been achieved as 94.87%. The proposed method is also analyzed on publicly available UTD-MHA and UR-Fall dataset. The classification accuracies are achieved as 83% and 95.52%respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Archana K, Reddy PB (2018) To detect abnormal event at ATM system by using image processing based on IOT technologies. Int J Eng Technol 7(3):1000–1004

    Article  Google Scholar 

  2. Batiz-Lazo, Bernardo Reid, and Robert J. K. (2008). Evidence from the patent record on the development of cash dispensing technology. Munich Personal RePEc Archive. p. 4. Retrieved 27 April 2015.

  3. Beddiar DR, Nini B, Sabokrou M, Hadid A (2020) Vision-based human activity recognition: a survey. Multimed Tools Appl 79(41):30509–30555

    Article  Google Scholar 

  4. Bhatt P, Thakker B (2020) Isolating botnet attacks using bootstrap aggregating Surflex-PSIM classifier in IoT. J Intell Fuzzy Syst 38(2):1827–1840

    Article  Google Scholar 

  5. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140

    Article  MATH  Google Scholar 

  6. Chen C, Jafari R, Kehtarnavaz N (2015) UTD-MHAD: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor, proceedings of IEEE international conference on image processing. Canada

  7. du Plooy R, Venter PJ (2021) A comparison of artificial neural networks and bootstrap aggregating ensembles in a modern financial derivative pricing framework. J Risk Financial Manag 14(6):254

    Article  Google Scholar 

  8. Evangelidis G, Singh G, Horaud R (2014) Skeletal quads human action recognition using joint quadruples, international conference on pattern recognition (ICPR). Stockholm, Sweden. https://doi.org/10.1109/ICPR.2014.772

  9. Everts I, van Gemert JC, Gevers T (2013) Evaluation of color STIPs for human action recognition, proc. IEEE Conf Comput Vision Pattern Recogn:2850–2857

  10. Gowayyed MA, Torki M, Hussein ME, El-Saban M (2013) Histogram of oriented displacements (HOD): describing trajectories of human joints for action recognition. Int joint Conf Artif Intell. 1351–1357.

  11. How, K. W., Han, P. Y., Yin, O. S., & Yen, Y. H. (2021). Spatiotemporal spectral histogramming analysis in hand gesture signature recognition. J Intell Fuzzy Syst, (preprint), 1-12.

  12. Hu L, Xu J (2017) A spatio-temporal convolutional neural network for skeletal action recognition, Int Conf neural inform process. 377-385.

  13. Huang T, Ru SR, Zeng ZH, Zhang L (2021) Research on motion recognition algorithm based on bag-of-words model. Microsyst Technol 27(4):1647–1654

    Article  Google Scholar 

  14. Kajendran P, Pravin A (2017) Enhancement of security related to ATM installations to detect misbehavior activity of unknown person using video analytics. ARPN J Eng Appl Sci 12:21

    Google Scholar 

  15. Sanaz Kianoush, Stefano Savazzi, Federico Vicentini, Vittorio Rampa, and Matteo Giussani (2017). Device-Free RF Human Body Fall Detection and Localization in Industrial Workplaces. IEEE Int Things J. 4(2).

  16. Krishnaveni B, Sridhar S (2017) Partially occluded face recognition using dynamic approach. Int J Sci Eng Technol Res 5(12):3341–3347

    Google Scholar 

  17. Kuehne H, Jhuang H, Stiefelhagen R, Serre T (2011) HMDB: a large video database for human motion recognition, proc. In: IEEE international conference in computer vision(ICCV), pp 2556–2563

    Google Scholar 

  18. Kumar, P., Gangal, A., & Kumari, S. (2021). Prognosis of breast cancer by implementing machine learning algorithms using modified bootstrap aggregating. In innovations in computational intelligence and computer vision (pp. 561–569). Springer, Singapore.

  19. Kwolek B, Kepski M (2014) Human fall detection on embedded platform using depth maps and wireless accelerometer. Comput Methods Prog Biomed 117(3):489–501 ISSN 0169-2607

    Article  Google Scholar 

  20. Liu J, Shahroudy A, Xu D, Kot AC, Wang G (2017) Skeleton-based action recognition using Spatio-temporal LSTM network with trust gates. Transactions on Pattern Analysis and Machine Intelligence, IEEE

    Google Scholar 

  21. Liu J, Zhang R, Han G, Sun N, Kwong S (2021) Video action recognition with visual privacy protection based on compressed sensing. J Syst Archit 113:101882

    Article  Google Scholar 

  22. Mahbub U, Imtiaz H, Ahad MAR (2013) Action recognition based on statistical analysis from clustered flow vectors. Signal, Image and Video Processing, pp 1–11

    Google Scholar 

  23. Mettes P, Thong W, Snoek CG (2021) Object priors for classifying and localizing unseen actions. Int J Comput Vis 129(6):1954–1971

    Article  Google Scholar 

  24. Ni B, Moulin P, Yang X, Yan S (2015) Motion part regularization: improving action recognition via trajectory group selection, in proc. IEEE Comput Soc Conf Comput vision Patt Recogn (CVPR). 3698–3706.

  25. Nievas EB, Suarez OD, García GB, Sukthankar R (2011) Violence detection in video using computer vision techniques, computer analysis of images and patterns. Springer, Berlin Heidelberg, pp 332–339

    Book  Google Scholar 

  26. Sadanand S, Corso JJ (2012) Action bank: a high-level representation of activity in video, proc. IEEE Conf Comput Vision Patt Recogn:1234–1241

  27. Scott MS (2001) Robbery at automated teller machines. US Department of Justice, Office of Community Oriented Policing Services

  28. Sharma N (2012) Analysis of different vulnerabilities in auto teller machine transactions. J Global Res Comput Sci 3(3):38–40

    Google Scholar 

  29. Shin J, Im CH (2020) Performance improvement of near-infrared spectroscopy-based brain-computer interface using regularized linear discriminant analysis ensemble classifier based on bootstrap aggregating. Front Neurosci 14:168

    Article  Google Scholar 

  30. Sichao L, Nakamura Y, Miwa H (2020) Gesture-based human-machine Interface system by using omnidirectional camera. In international conference on intelligent networking and collaborative systems (pp. 56-66). Springer, Cham.

  31. Sikandar T, Ghazali KH, Rabbi MF (2019) ATM crime detection using image processing integrated video surveillance: a systematic review. Multimedia Systems 25(3):229–251

    Article  Google Scholar 

  32. Sikandar T, Samsudin WNAW, Rabbi MF, Ghazali KH (2020) An efficient method for detecting covered face scenarios in ATM surveillance camera. SN Comput Sci 1(3):1–11

    Article  Google Scholar 

  33. Singh R, Kushwaha AKS, Srivastava R (2019) Multi-view recognition system for human activity based on multiple features for video surveillance system. Multimed Tools Appl 78(12):17165–17196

    Article  Google Scholar 

  34. Tao L, Vidal R (2015) Moving Poselets: a discriminative and interpretable skeletal motion representation for action recognition. IEEE Int Conf Comp Vision Workshops:61–69

  35. Tripathi V, Mittal A, Gangodkar D, Kanth V (2016) Real time security framework for detecting abnormal events at ATM installations. 16:1–11. https://doi.org/10.1007/s11554-016-0573-3

  36. Tripathi V, Gangodkar D, Mittal A, Kanth V (2017) Robust action recognition framework using segmented block and distance mean histogram of gradient approach. J Procedia Comput Sci 115:493–500

    Article  Google Scholar 

  37. Vemulapalli R, Arrate F, Chellappa R (2014) Human action recognition by representing 3D skeletons as points in a lie group, in: IEEE conference on computer vision and pattern recognition (CVPR)

  38. Viji, S., Kannan, R., & Jayalashmi, N. Y. (2021). Intelligent anomaly detection model for ATM booth surveillance using machine learning algorithm: intelligent ATM Survillance model. In 2021 international conference on computing, communication, and intelligent systems (ICCCIS) (pp. 1007-1012). IEEE.

  39. Zhang T, Li J, Jia W, Sun J, Yang H (2018) Fast and robust occluded face detection in ATM surveillance. Pattern Recogn Lett 107:33–40

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Graphic Era Deemed to be University, Dehradun, India

    Awadhesh Kumar Srivastava, Vikas Tripathi, Bhaskar Pant & Devesh Pratap Singh

  2. Kellton Tech Solutions Limited, Gurugram, India

    Awadhesh Kumar Srivastava

  3. NIT Agartala, Agartala, India

    Munesh Chandra Trivedi

Authors
  1. Awadhesh Kumar Srivastava
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Vikas Tripathi
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Bhaskar Pant
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Devesh Pratap Singh
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Munesh Chandra Trivedi
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Awadhesh Kumar Srivastava.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Srivastava, A.K., Tripathi, V., Pant, B. et al. Automatic and multimodal nuisance activity detection inside ATM cabins in real time. Multimed Tools Appl 82, 5113–5132 (2023). https://doi.org/10.1007/s11042-022-12313-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12313-4

Keywords