Advertisement

Efficient Motion Encoding Technique for Activity Analysis at ATM Premises

  • Prateek BajajEmail author
  • Monika Pandey
  • Vikas Tripathi
  • Vishal Sanserwal
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 713)

Abstract

Automated teller machines (ATMs) have become the predominant banking channel for the majority of customer transactions. However, despite the multitudinous advantages of ATM, it lacks in providing security measures against ATM frauds. Video surveillance is one of the prominent measures against ATM frauds. In this paper, we present an approach that can be used for activity recognition in small premises such as ATM rooms by encoding the motion in images. We have used gradient-based descriptor (HOG) to extract features from image sequences. The features obtained are classified using random forest classifier. Our employed method is successful in determining abnormal and normal human activities both in case of single and multiple personnel with an average accuracy of 97%.

References

  1. 1.
    Wang, C., Komodakis, N., Paragios, N.: Markov random field modeling, inference & learning in computer vision & image understanding. A survey. Comput. Vis. Image Underst. 117(11), 1610–1627 (2013)CrossRefGoogle Scholar
  2. 2.
    Chen, P., Chen, X., Jin, B., Zhu, X.: Online EM algorithm for background subtraction. Procedia Eng. 29, 164–169 (2012)CrossRefGoogle Scholar
  3. 3.
    Blanco Adán, C.R., Jaureguizar, F., García, N.: Bayesian visual surveillance: a model for detecting and tracking a variable number of moving objects. In: 18th IEEE International Conference on IEEE Image Processing (ICIP), pp. 1437–1440 (2011)Google Scholar
  4. 4.
    Boateng, R.: Developing e-banking capabilities in a Ghanaian Bank. Preliminary lessons. J. Internet Bank. Commer. 213–234 (2006)Google Scholar
  5. 5.
    Kumar, P., Mittal, A., Kumar, P.: Study of robust and intelligent surveillance in visible and multi-modal framework. Informatica (Slovenia) 32(1), 63–77 (2008)Google Scholar
  6. 6.
    Cucchiara, R.: Multimedia surveillance systems. In: Proceedings of the Third ACM International Workshop on Video Surveillance & Sensor Networks, pp. 3–10. ACM (2005)Google Scholar
  7. 7.
    Babu, R.V., Ramakrishnan, K.R.: Compressed domain human motion recognition using motion history information. In: 2003 International Conference on Image Processing, vol. 3, pp. 321–324. IEEE (2003)Google Scholar
  8. 8.
    Gupta, R., Jain, A., Rana, S.: A novel method to represent repetitive and overwriting activities in motion history images. In: 2013 International Conference on Communications and Signal Processing (ICCSP), pp. 556–560. IEEE (2013)Google Scholar
  9. 9.
    Zhou, F., De la Torre, F., Hodgins, J.K.: Hierarchical aligned cluster analysis for temporal clustering of human motion. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 582–596 (2013)CrossRefGoogle Scholar
  10. 10.
    Bradski, G.R., Davis, J.: Motion segmentation and pose recognition with motion history gradients. Mach. Vis. Appl. 13(3), 174–184 (2002)CrossRefGoogle Scholar
  11. 11.
    Pandey, M., Sanserwal, V., Tripathi, V.: Intelligent vision based surveillance framework for ATM premises (2016)Google Scholar
  12. 12.
    Sujith, B.: Crime detection and avoidance in ATM. Int. J. Comput. Sci. Inf. Technol. 6068–6071 (2014)Google Scholar
  13. 13.
    Davis, J.W., Bobick, A.F.: The representation and recognition of human movement using temporal templates. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 928–934 (1997)Google Scholar
  14. 14.
    Garrido-Jurado, S., Muñoz-Salinas, R., Madrid-Cuevas, F.J., Marýn-Jiménez, M.J.: Automatic generation and detection of highly reliable ûducial markers under occlusion. Pattern Recognit. 47(6), 2280–2292 (2016)CrossRefGoogle Scholar
  15. 15.
    Ahad, M.A.R., Ogata, T., Tan, J.K., Kim, H.S., Ishikawa, S.: Directional motion history templates for low resolution motion recognition. In: 34th Annual Conference of IEEE, pp. 1875–1880 (2008)Google Scholar
  16. 16.
    Ahad, M.A.R., Ogata, T., Tan, J.K., Kim, H.S., Ishikawa, S.: Template-based human motion recognition for complex activities. IEEE International Conference, pp. 673–678 (2008)Google Scholar
  17. 17.
    Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976–990 (2010)CrossRefGoogle Scholar
  18. 18.
    Al-Berry, M.N., et al.: Action recognition using stationary wavelet-based motion images. Intelligent Systems, pp. 743–753 (2014). Springer International Publishing (2015)Google Scholar
  19. 19.
    Hu, R., Collomosse, J.: A performance evaluation of gradient field hog descriptor for sketch based image retrieval. Comput. Vis. Image Underst. 117(7), 790–806 (2013)CrossRefGoogle Scholar
  20. 20.
    Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551–3558 (2013)Google Scholar
  21. 21.
    Hu, M.K.: Visual pattern recognition by moment invariants. IEEE Trans. Inf. Theory 8(2), 179–187 (1962)Google Scholar
  22. 22.
    Amato, A., Lecce, V.D.: Semantic classification of human behaviors in video surveillance systems. J. WSEAS Trans. Comput. 10, 343–352 (2011)Google Scholar
  23. 23.
    Chen, Q., Wu, R., Ni, Y., Huan, R., Wang, Z.: Research on human abnormal behavior detection and recognition in intelligent video surveillance. J. Comput. Inf. Syst. 9(1), 289–296 (2011)Google Scholar
  24. 24.
    Srestasathiern, P., Yilmaz, A.: Planar shape representation and matching under projective transformation. Comput. Vis. Image Underst. 115(11), 1525–1535 (2011)CrossRefGoogle Scholar
  25. 25.
    Sanserwal, V., Pandey, M., Tripathi, V., Chan, Z.: Comparative analysis of various feature descriptors for efficient ATM surveillance framework (2017)Google Scholar
  26. 26.
    Tripathi, V., et al.: Robust abnormal event recognition via motion and shape analysis at ATM installations. J. Electr. Comput. Eng. (2015)Google Scholar
  27. 27.
    Rashwan, H.A., et al.: Illumination robust optical flow model based on histogram of oriented gradients. In: German Conference on Pattern Recognition, pp. 354–363. Springer, Berlin, Heidelberg (2013)Google Scholar
  28. 28.
    Hirabayashi, M., et al.: GPU implementations of object detection using HOG features and deformable models. In: IEEE 1st International Conference on IEEE Cyber-Physical Systems, Networks, and Applications (CPSNA), pp. 106–111 (2013)Google Scholar
  29. 29.
    Huang, C., Huang, J.: A fast HOG descriptor using lookup table and integral image (2017). arXiv:1703.06256
  30. 30.
    Uijlings, J., Duta, I.C., Sangineto, E., Sebe, N.: Video classification with densely extracted HOG/HOF/MBH features: an evaluation of the accuracy/computational efficiency trade-off. Int. J. Multimed. Inf. Retr. 4(1), 33–44 (2015)CrossRefGoogle Scholar
  31. 31.
    Kennedy, R., Taylor, C.J.: Optical flow with geometric occlusion estimation and fusion of multiple frames. In: International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 364–377. Springer International Publishing (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Prateek Bajaj
    • 1
    Email author
  • Monika Pandey
    • 1
  • Vikas Tripathi
    • 1
  • Vishal Sanserwal
    • 1
  1. 1.Department of Computer Science and EngineeringGraphic Era UniversityDehradunIndia

Personalised recommendations