Detection of Anomalous Gait as Forensic Gait in Residential Units Using Pre-trained Convolution Neural Networks

  • Hana’ Abd Razak
  • Ali Abd Almisreb
  • Nooritawati Md. TahirEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1130)


One of the advantages of transfer learning technique is its capability to learn new dataset using its finest pre-trained architecture. Other advantages of this technique are small dataset requirements along with faster learning process that could yield high accuracy results. Hence in this paper, anomalous gait detection or also known as forensic gait during housebreaking crime at the gate of residential units is discussed with transfer learning technique based on five popular pre-trained convolution neural networks (CNNs) as classifiers. High accuracy and sensitivity are achieved from remodeled of the pre-trained CNNs for the learning process, offline test, and real-time test. The accuracy attained from remodeled of the pre-trained CNNs have pledged high potential towards developing the forensic intelligent surveillance technique.


Anomalous behavior Forensic gait Pre-trained CNN Remodeled pre-trained CNN Transfer learning 



This research is funded by Research Management Centre (RMC), Universiti Teknologi MARA (UiTM), Shah Alam, Selangor, Malaysia Grant No: 600-IRMI/MyRA5/3/BESTARI (041/2017). The first author would like to thank Ministry of Education (MOE) Malaysia for the scholarship awarded under MyBrain MyPhD as well as Faculty of Electrical Engineering UiTM Shah Alam for all the support given during this research. In addition, special thanks to Royal Malaysia Police for providing legal information and assisting in developing forensic gait features.


  1. 1.
    Sidhu, A.C.P.A.S.: The rise of crime in malaysia: an academic and statistical analysis. J. Kuala Lumpur R. Malaysia Police Coll. 4, 1–28 (2005)Google Scholar
  2. 2.
    Hamid, L.A., Toyong, N.M.P.: Rural area, elderly people and the house breaking crime. Proc. - Soc. Behav. Sci. 153, 443–451 (2014)CrossRefGoogle Scholar
  3. 3.
    Soh, M.C.: Crime and urbanization: revisited malaysian case. Proc. Soc. Behav. Sci. 42(July 2010), 291–299 (2012)CrossRefGoogle Scholar
  4. 4.
    Marzbali, M.H., Abdullah, A., Razak, N.A., Tilaki, M.J.M.: The relationship between socio-economic characteristics, victimization and CPTED principles: evidence from the MIMIC model. Crime Law Soc. Chang. 58(3), 351–371 (2012)CrossRefGoogle Scholar
  5. 5.
    Chris, K., Natalia, C.-M., Carys, T., Rebbecca, A.: Burglary, vehicle and violent crime. In: The 2001 British Crime Survey. First Results, England and Wales, vol. 18, pp. 23–27. Home Office Statistical Bulletin, Queen Anne’s Gate, London (2001)Google Scholar
  6. 6.
    Van Dijk, J.J.M., Mayhew, P., Killias, M.: Victimization rates. In :Experiences of Crime across the World: Key findings of the 1989 International Crime Survey, pp. 23–25. Kluwer Law and Taxation Publishers, Deventer (1990)Google Scholar
  7. 7.
    Murphy, R., Eder, S.: Acquisitive and other property crime. In: Flatley, J., Kershaw, C., Smith, K., Chaplin, R., Moon, D. (eds.) Crime in England and Wales 2009/10, Third Edit., vol. 12, pp. 79–87. Home Office Statistical Bulletin, Marsham Street, London (2010)Google Scholar
  8. 8.
    Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 1–72 (2009)Google Scholar
  9. 9.
    Lawson, W., Hiatt, L.: Detecting anomalous objects on mobile platforms. In: 2016 IEEE Conference on Computer Vision Pattern Recognition Working, pp. 1426–1433 (2016)Google Scholar
  10. 10.
    Mohammadi, S., Perina, A., Kiani, H., Murino, V.: Angry crowd : detecting violent events in videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision - ECCV 2016. LNCS, vol. 9911, pp. 3–18. Springer, Cham (2016)CrossRefGoogle Scholar
  11. 11.
    Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of IEEE Computing Socitey Conference on Computer Vision and Pattern Recognition, pp. 6479–6488 (2018)Google Scholar
  12. 12.
    Tay, N.C., Tee, C., Ong, T.S., Goh, K.O.M., Teh, P.S.: A robust abnormal behavior detection method using convolutional neural network. In: Alfred, R., Lim, Y., Ibrahim, A., Anthony, P. (eds.) Computational Science and Technology. Fifth International Conference on Computational Science and Technology. Lecture Notes in Electrical Engineering, vol. 481, pp. 37–47. Springer, Singapore (2019)Google Scholar
  13. 13.
    Al-Dhamari, A., Sudirman, R., Mahmood, N.H.: Abnormal behavior detection in automated surveillance videos: a review. J. Theor. Appl. Inf. Technol. 95(19), 5245–5263 (2017)Google Scholar
  14. 14.
    Delgado, B., Tahboub, K., Delp, E.J.: Automatic detection of abnormal human events on train platforms. In: IEEE National Aerospace and Electronics Conference (NAECON 2014), pp. 169–173 (2014)Google Scholar
  15. 15.
    Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  16. 16.
    Almisreb, A.A., Jamil, N., Md Din, N.: Utilizing AlexNet deep transfer learning for ear recognition. In: 2018 Fourth International Conference on Information Retrieval and Knowledge Management, pp. 8–12 (2018)Google Scholar
  17. 17.
    Andrew, J.T.A., Tanay, T., Morton, E.J., Griffin, L.D.: Transfer representation-learning for anomaly detection. In: Proceedings of 33rd International Conference on Machine Learning Research, New York, USA, vol. 48, pp. 1–5 (2016)Google Scholar
  18. 18.
    Ali, A.M., Angelov, P.: Anomalous behaviour detection based on heterogeneous data and data fusion. Soft. Comput. 22(10), 3187–3201 (2018)CrossRefGoogle Scholar
  19. 19.
    Sabokrou, M., Fayyaz, M., Fathy, M., Moayed, Z., Klette, R.: Deep-anomaly : fully convolutional neural network for fast anomaly detection in crowded scenes. J. Comput. Vis. Image Underst. 1–30 (2018). (arXiv00866v2 [cs.CV])Google Scholar
  20. 20.
    Huang, Z., Pan, Z., Lei, B.: Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data. Remote Sens. 9(907), 1–21 (2017)Google Scholar
  21. 21.
    Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? Adv. Neural. Inf. Process. Syst. 27, 1–14 (2014)Google Scholar
  22. 22.
    Chollet, F.: Deep learning for computer vision: using a pretrained convnet. In: Deep Learning with Python, pp. 143–159. Manning, Shelter Island(2018)Google Scholar
  23. 23.
    Ali, A.M., Angelov, P.: Applying computational intelligence to community policing and forensic investigations. In: Bayerl, P.S., Karlovic, R., Akhgar, B., Markarian, G. (eds.) Advanced Sciences and Technologies for Security Applications: Community Policing - A European Perspective, pp. 231–246. Springer, Cham (2017)CrossRefGoogle Scholar
  24. 24.
    Lu, J., Yan, W.Q., Nguyen, M.: Human behaviour recognition using deep learning. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 1–6 (2018)Google Scholar
  25. 25.
    Hospedales, T., Gong, S., Xiang, T.: A Markov clustering topic model for mining behaviour in video. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1–8 (2009)Google Scholar
  26. 26.
    Zhang, C., Li, R., Kim, W., Yoon, D., Patras, P.: Driver behavior recognition via interwoven deep convolutional neural nets with multi-stream inputs. arXiv:1811.09128v1 [cs.CV], pp. 1–10 (2018)
  27. 27.
    Pang, Y., Syu, S., Huang, Y., Chen, B.: An advanced deep framework for recognition of distracted driving behaviors. In: 2018 IEEE 7th Global Conference on Consumer Electronics, pp. 802–803 (2018)Google Scholar
  28. 28.
    Arifoglu, D., Bouchachia, A.: Activity recognition and abnormal behaviour detection with recurrent neural networks. In: 14th International Conference on Mobile Systems and Pervasive Computing (MobiSPC 2017), vol. 110, pp. 86–93 (2017)Google Scholar
  29. 29.
    Kröse, B., van Oosterhout, T., Englebienne, G.: Video surveillance for behaviour monitoring in home health care. Proc. Meas. Behav. 2014, 2–6 (2014)Google Scholar
  30. 30.
    Leixian, S., Zhang, Q.: Fall behavior recognition based on deep learning and image processing. Int. J. Mob. Comput. Multimed. 9(4), 1–16 (2019)Google Scholar
  31. 31.
    Xu, H., Li, L., Fang, M., Zhang, F.: Movement human actions recognition based on machine learning. Int. J. Online Biomed. Eng. 14(4), 193–210 (2018)Google Scholar
  32. 32.
    Datta, A., Shah, M., Da Vitoria Lobo, N.: Person-on-person violence detection in video data. In: Proceedings of International Conference on Pattern Recognition, vol. 16, no. 1, pp. 433–438 (2002)Google Scholar
  33. 33.
    Gao, Y., Liu, H., Sun, X., Wang, C., Liu, Y.: Violence detection using oriented VIolent flows. Image Vis. Comput. 48–49, 37–41 (2016)CrossRefGoogle Scholar
  34. 34.
    Kooij, J.F.P., Liem, M.C., Krijnders, J. D., Andringa, T., Gavrila, D.M.: Multi-modal human aggression detection. Comput. Vis. Image Underst. 1–35 (2016)Google Scholar
  35. 35.
    Patil, S., Talele, K.: Suspicious movement detection and tracking based on color histogram. In: 2015 International Conference on Communication, Information and Computing Technology, pp. 1–6 (2015)Google Scholar
  36. 36.
    Zhu, Y., Wang, Z.: Real-time abnormal behavior detection in elevator. In: Zhang, Z., Huang, K. (eds.) Intelligent Visual Surveillance. IVS 2016. Communications in Computer and Information Science, vol. 664, pp. 154–161. Springer, Singapore (2016)CrossRefGoogle Scholar
  37. 37.
    Ben Ayed, M., Abid, M.: Suspicious behavior detection based on DECOC classifier. In: 18th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering, pp. 594–598 (2017)Google Scholar
  38. 38.
    Yu, B.: Design and implementation of behavior recognition system based on convolutional neural network. In: ITM Web Conference, vol. 12, no. 01025, pp. 1–5 (2017)Google Scholar
  39. 39.
    He, L., Wang, D., Wang, H.: Human abnormal action identification method in different scenarios. In: Proceedings of 2011 2nd International Conference on Digital Manufacturing and Automation ICDMA 2011, pp. 594–597 (2011)Google Scholar
  40. 40.
    Min, W., Cui, H., Han, Q., Zou, F.: A scene recognition and semantic analysis approach to unhealthy sitting posture detection during screen-reading. Sensors (Basel) 18(9), 1–22 (2018)CrossRefGoogle Scholar
  41. 41.
    Nazare, T.S., de Mello, R.F., Ponti, M.A.: Are pre-trained CNNs good feature extractors for anomaly detection in surveillance videos? arXiv:1811.08495v1 [cs.CV], pp. 1–6 (2018)
  42. 42.
    Lee, J., Kim, H., Lee, J., Yoon, S.: Transfer learning for deep learning on graph-structured data. In: Proceedings of Thirty-First AAAI Conference on Artificial Intelligence, pp. 2154–2160 (2017)Google Scholar
  43. 43.
    Bell, M.O.: Computational Complexity of network reliability analysis: an overview. IEEE Trans. Reliab. R-35(3), 230–239 (1986)CrossRefGoogle Scholar
  44. 44.
    The Mathworks: Series network for deep learning – MATLAB (2016). Accessed 12 June 2019
  45. 45.
    Vedaldi, A., Lenc, K., Gupta, A.: MatConvNet - convolutional neural networks for MATLAB. arXiv:1412.4564 [cs.CV], pp. 1–59 (2015)
  46. 46.
    The Mathworks: Directed acyclic graph (DAG) network for deep learning - MATLAB (2017). Available: Accessed: 12 June 2019
  47. 47.
    Sahner, R.A., Trivedi, K.S.: Performance and reliability analysis using directed acyclic graphs. IEEE Trans. Softw. Eng. SE-13(10), 1105–1114 (1987)CrossRefGoogle Scholar
  48. 48.
    Bang-Jensen, J., Gutin, G.Z.: Acyclic digraphs. In: Diagraphs: Theory, Algorithms and Applications, Second Edition. Monographs in Mathematics, pp. 32–34. Springer, London (2009)Google Scholar
  49. 49.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advance in Neural Information Processing Systems, vol. 25, pp. 1–9 (2012)Google Scholar
  50. 50.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representation (ICLR 2015), pp. 1–14 (2015)Google Scholar
  51. 51.
    Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision Pattern Recognition (CVPR 2015), pp. 1–9 (2015)Google Scholar
  52. 52.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision Pattern Recognition (CVPR 2016), pp. 2818–2826 (2016)Google Scholar
  53. 53.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision Pattern Recognition, pp. 770–778 (2016)Google Scholar
  54. 54.
    Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv:1605.07146v4 [cs.CV], pp. 1–15 (2017)
  55. 55.
    Liu, Y.Y., Slotine, J.-J., Barabasi, A.-L.: Control centrality and hierarchical structure in complex networks. PLoS One 7(9), 1–7 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Hana’ Abd Razak
    • 1
  • Ali Abd Almisreb
    • 2
  • Nooritawati Md. Tahir
    • 1
    Email author
  1. 1.Faculty of Electrical EnginneringUniversiti Teknologi MARAShah AlamMalaysia
  2. 2.International University of SarajevoSarajevoBosnia and Herzegovina

Personalised recommendations