Advertisement

A Review of Gait Behavior Recognition Methods Based on Wearable Devices

  • Chang LiuEmail author
  • Jijun Zhao
  • Zhongcheng Wei
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 980)

Abstract

As a new biometric recognition technique, gait behavior recognition is mainly based on the individual behavior analysis of human walking. Among them, the recognition of gait classification is a key step and an important task in the process of gait behavior recognition. Firstly, this paper analyzes the factors of data noise, and summarizes the methods of data preprocessing. Secondly, it analyzes and discusses the classification of gait features. Then it compares the algorithms of gait behavior classification and recognition; The gait classification recognition method based on Hidden Markov is reviewed, which has certain theoretical guiding significance and application value.

Keywords

HMM Gait behavior recognition Feature extraction Classification recognition 

Notes

Acknowledgments

This paper is found by Science and Technology Research and Development Plan Project of Handan (No. 1721203048).

References

  1. 1.
    Dawson, M.R.: “Gait recognition.” Final Thesis Report, Department of Computing, Imperial College of Science, Technology & Medicine, London (2002)Google Scholar
  2. 2.
    Xingzhi, Z., Chensheng, W., Feng, L.: Gait recognition review. Software 34(4), 160–164 (2013). (in Chinese)Google Scholar
  3. 3.
    Cho, C.W., Chao, W.H., Lin, S.H., Chen, Y.Y.: A vision-based analysis system for gait recognition in patients with Parkinson’s disease. Expert Syst. Appl. 36(3), 7033–7039 (2009)CrossRefGoogle Scholar
  4. 4.
    Stevenage, S.V., Nixon, M.S., Vince, K.: Visual analysis of gait as a cue to identity. Appl. Cogn. Psychol. Official J. Soc. Appl. Res. Mem. Cogn. 13(6), 513–526 (1999)Google Scholar
  5. 5.
    Liang, W., Weiming, H.: Gait based identification. J. Comput. Sci. 26(3), 353–360 (2003). (in Chinese)Google Scholar
  6. 6.
    Niyogi, S.A., Adelson, E.H.: Analyzing gait with spatiotemporal surfaces. In: Proceedings of the 1994 IEEE Workshop on Motion of Non-Rigid and Articulated Objects, pp. 64–69. IEEE (1994)Google Scholar
  7. 7.
    Mantyjarvi, J., Lindholm, M., Vildjiounaite, E., et al.: Identifying users of portable devices from gait pattern with accelerometers. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2005), vol. 2, pp. 973–976. IEEE (2005)Google Scholar
  8. 8.
    Mannini, A., Sabatini, A.M.: A smartphone-centered wearable sensor network for fall risk assessment in the elderly. In: Proceedings of the 10th EAI International Conference on Body Area Networks. ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), pp. 167–172 (2015)Google Scholar
  9. 9.
    Lin, W., Zhongmin, W.: User behavior recognition model for location independent mobile phone. Comput. Appl. Res. 32(01), 63–66 (2015). (in Chinese)Google Scholar
  10. 10.
    Bao, L., Stephen, I.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) Pervasive 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-24646-6_1CrossRefGoogle Scholar
  11. 11.
    Wang, T., Wang, Z., Zhang, D., et al.: Recognizing Parkinsonian gait pattern by exploiting fine-grained movement function features. ACM Trans. Intell. Syst. Technol. (TIST) 8(1), 6 (2016)Google Scholar
  12. 12.
    Joy, J., Peter, S., John, N.: Denoising using soft thresholding. Int. J. Adv. Res. Electr. Electron. Instrum. Eng. 2(3), 1027–1032 (2013)Google Scholar
  13. 13.
    Donoho, D.L., Johnstone, I.M.: Adapting to unknown smoothness via wavelet shrinkage. J. Am. Stat. Assoc. 90(432), 1200–1224 (1995)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Xianbing, P.: Performance analysis of an improved wavelet threshold denoising method. Microcomput. Inf. (03S), 112–113 (2006). (in Chinese)Google Scholar
  15. 15.
    Haofan, D., Shuang, C.: Research on de-noising method based on MATLAB wavelet. Comput. Simul. 20(7), 119–122 (2003). (in Chinese)Google Scholar
  16. 16.
    Xiaona, Q., Tengyu, Z., Xitai, W.: Experimental study on the influence of walking speed on gait parameters. Chin. J. Rehabil. Med. 27(3), 257–259 (2012). (in Chinese)Google Scholar
  17. 17.
    Xueyan, H., Xiaoping, H.: Gait characteristics in normal adults. Chin. Rehabil. Theor. Pract. 12(10), 855–857 (2006). (in Chinese)Google Scholar
  18. 18.
    Datta, D., Heller, B., Howitt, J.: A comparative evaluation of oxygen consumption and gait pattern in amputees using Intelligent Prostheses and conventionally damped knee swing-phase control. Clin. Rehabil. 19(4), 398–403 (2005)CrossRefGoogle Scholar
  19. 19.
    Jidong, Y., Zhihai, W., Wei, Z.: K nearest neighbor classifier for complex time series. softw. J. 28(11), 3002–3017 (2017). (in Chinese)Google Scholar
  20. 20.
    Weiling, C., Dongxia, C.: The influence of data normalization method on K nearest neighbor classifier. Comput. Eng. 36(22), 175–177 (2010). (in Chinese)Google Scholar
  21. 21.
    Li, C., Jing, C.: Multi feature fusion method based on support vector machine and k- nearest neighbor classifier. Comput. Appl. 29(03), 833–835 (2009). (in Chinese)Google Scholar
  22. 22.
    Kai, W., Yongmei, S., Hong, Z., Yang, W.: Recognition of gait behavior based on feature combination in body area network. Sci. China: Inf. Sci. 43(10), 1353–1364 (2013). (in Chinese)Google Scholar
  23. 23.
    Xiuyu, X., Hongyu, L., Wu, H.: Gait classification based on acceleration sensors. Sens. World 19(04), 10–13 (2013). (in Chinese)Google Scholar
  24. 24.
    Qi, Y., Dingyu, X.: Dynamic and static information fusion and gait recognition in dynamic Bayesian networks. J. Image Graph. China 17(07), 783–790 (2012). (in Chinese)Google Scholar
  25. 25.
    Qi, Y., Dingyu, X.: Gait recognition based on dual-scale dynamic Bayesian networks and multiple information fusion. J. Electron. Inf. Technol. 34(05), 1148–1153 (2012). (in Chinese)Google Scholar
  26. 26.
    Xixi, L., Hong, L.: Bayesian gait recognition method based on the triangulation of leg. Comput. Eng. Appl. 17, 195–197+21 (2008). (in Chinese)Google Scholar
  27. 27.
    Bing, C., Li, F., Xing, W.: A survey of gait recognition methods based on SVM. Measur. Control Technol. 35(08), 1–5 (2016). (in Chinese)Google Scholar
  28. 28.
    Xin, S., Luning, L., Qingyu, X.: Unusual gait recognition based on quadratic feature extraction and SVM. Chin. J. Sci. Instrum. 32(03), 673–677 (2011). (in Chinese)Google Scholar
  29. 29.
    Bo, Y., Yumei, W.: Gait recognition algorithm based on wavelet transform and support vector machine. J. Image Graph. 06, 1055–1063 (2007). (in Chinese)Google Scholar
  30. 30.
    Zhaojue, X., Jia, L., Dong, M.: A new method of gait recognition based on support vector machines. J. Tianjin Univ. 01, 78–82 (2007). (in Chinese)Google Scholar
  31. 31.
    Qiuhong, Z., Jin, S., Xinfeng, Y.: Simulation of gait recognition based on feature fusion and neural network. Comput. Simul. 29(08), 235–237+245 (2012). (in Chinese)Google Scholar
  32. 32.
    Xin, G., Lei, W., Bokai, X., Caiping, L.: Gait recognition based on supervised kohonen neural network. Acta Autom. Sin. 43(03), 430–438 (2017). (in Chinese)Google Scholar
  33. 33.
    Junkuan, Z.: Research on gait recognition based on BP neural network. China Secur. Z1, 99–101 (2016). (in Chinese)Google Scholar
  34. 34.
    Na, Y., Peng, Y.: Gait recognition using average influence value and probability neural network. J. Harbin Eng. Univ. 36(02), 181–185 (2015). (in Chinese)Google Scholar
  35. 35.
    Yuliang, M., Yunpeng, M., Zhinzeng, L.: GA-BP application of neural network in gait recognition of lower extremities. J. Trans. Technol. 26(09), 1183–1187 (2013). (in Chinese)Google Scholar
  36. 36.
    Xiuhui, W., Ke, Y.: Human gait recognition based on continuous density hidden Markov model. Pattern Recogn. Artif. Intell. 29(08), 709–716 (2016). (in Chinese)Google Scholar
  37. 37.
    Ping, L.: Gait recognition method based on haar wavelet and fusion HMM. Comput. Appl. Softw. 30(03), 244–246+254 (2013). (in Chinese)Google Scholar
  38. 38.
    Tao, Y., Jianhua, Z.: Gait recognition method based on bayesian rule and HMM. Chin. J. Comput. 35(02), 2386–2396 (2012). (in Chinese)Google Scholar
  39. 39.
    Qianjin, Z., Yanzeng, S., Suli, X.: Gait recognition based on the fusion of continuous hmm and static appearance information models. Microelectron. Comput. 26(03), 45–48 (2009). (in Chinese)Google Scholar
  40. 40.
    Dali, G., Qingjiang, W.: Gait identification based on HMM. Comput. Eng. Appl. 16, 53–56+166 (2006). (in Chinese)Google Scholar
  41. 41.
    Baum, L.E., Petriem, T.: Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37(6), 1554–1563 (1966)MathSciNetCrossRefGoogle Scholar
  42. 42.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  43. 43.
    Baker, J.: The DRAGON system–an overview. IEEE Trans. Acoust. Speech Signal Process. 23(1), 24–29 (1975)CrossRefGoogle Scholar
  44. 44.
    Nádas, A., Nahamoo, D., Picheny, M.A.: On a model-robust training method for speech recognition. IEEE Trans. Acoust. Speech Signal Process. 36(9), 1432–1436 (1988)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Information and Electric EngineeringHebei University of EngineeringHandanChina

Personalised recommendations