Footsteps, as a main kind of behavioural trait are a universally available signal. However, it remains a challenging problem to construct a robust footstep authentication system. Since, in practise, footsteps are usually accompanied with noisy and environmental sounds, it is difficult to extract stable footstep features from the mixed sounds. This study describes a novel robust footstep identification system. To extract stable features from the footsteps mixed with noisy or environmental sounds, a robust acoustic local feature extraction method is proposed. In the proposed method, the main frequency components of footsteps are determined, and then their local distributions and variations in time–frequency domain are obtained and regarded as the acoustic local features. These local features are robust to white noise, pink noise and invariant to the intensity of the footsteps. However, the conventional pattern recognition methods are not suitable for them due to that these local features are observably different from the frequently used acoustic features, and so the authors introduce a Bayesian decision classifier to implement footstep identification. Theoretical and experimental results demonstrate that this system is relatively robust to white noise, pink noise, environmental sounds and yields a better classification performance compared with the existing methods.

References

1. 1)
  - 9. Heikkila, M., Pietikainena, M., Schmid, C.: ‘Description of interest regions with local binary patterns’, Pattern Recognit., 2009, 42, (3), pp. 425–436.
2. 2)
  - 4. Vajaria, H., Islam, T., Mohanty, P., et al: ‘Evaluation and analysis of a face and voice outdoor multi-biometric system’, Pattern Recognit. Lett., 2007, 28, pp. 1572–1580.
3. 3)
  - 21. Jain, A.K., Dubes, R.C.: ‘Algorithms for clustering data’ (Prentice-Hall Inc., Upper Saddle River, NJ, USA, 1998).
4. 4)
  - 12. Itai, A., Yasukawa, H.: ‘Footstep recognition with psycho-acoustics parameter’. Proc. of IEEE Asia Pacific Conf. on Circuits and Systems, 2006, pp. 992–995.
5. 5)
  - 18. Vera-Rodriguez, R., Mason, J.S.D., Fierrez, J., et al: ‘Analysis of spatial domain information for footstep recognition’, IET Comput. Vis., 2011, 5, (6), pp. 380–388.
6. 6)
  - 19. Vera-Rodriguez, R., Mason, J.S.D., Fierrez, J., et al: ‘Comparative analysis and fusion of spatiotemporal information for footstep recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (4), pp. 823–834.
7. 7)
  - 13. Itai, A., Yasukawa, H.: ‘Personal identification using footstep based on wavelets’. Proc. of Int. Symp. on Intelligent Signal Processing and Communication Systems, 2006, pp. 383–386.
8. 8)
  - 6. Mikolajczyk, K., Schmid, C.: ‘A performance evaluation of local descriptors’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (10), pp. 1615–1630.
9. 9)
  - 8. Lazebnik, S., Schmid, C., Ponce, J.: ‘A sparse texture representation using local affine regions’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (8), pp. 1265–1278.
10. 10)
  - 17. Qian, G., Zhang, J., Kidane, A.: ‘People identification using floor pressure sensing and analysis’, IEEE Sens. J., 2010, 10, (9), pp. 1447–1460.
11. 11)
  - 11. Shoji, Y., Itai, A., Yasukawa, H.: ‘Personal identification using footstep detection in in-door environment’, IEICE Trans. Fundam., 2005, E88-A, (8), pp. 53–54.
12. 12)
  - 1. Abhyankar, A., Schuckers, S.: ‘A novel biorthogonal wavelet network system for off-angle iris recognition’, Pattern Recognit., 2010, 43, pp. 987–1007.
13. 13)
  - 14. Itai, A., Yasukawa, H.: ‘Footstep classification using simple speech’, IEEE Int. Symp. on Circuits and Systems, 2008, pp. 3234–3237.
14. 14)
  - 15. de Carvalho, R.L., Rosa, P.F.F.: ‘Identification system for smart homes using footstep sounds’. IEEE Int. Symp. on Industrial Electronics, 2010, pp. 1639–1644.
15. 15)
  - 2. Pankanti, S., Prabhakar, S., Jain, A.K.: ‘On the individuality of fingerprints’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, pp. 1010–1025.
16. 16)
  - 16. Miyoshi, M., Mori, K., Kashihara, Y., et al: ‘Personal identification method using footsteps’. Proc. of SICE Annual Conf., 2011, pp. 1615–1620.
17. 17)
  - 10. Shoji, Y., Takasuka, T., Yasukawa, H.: ‘Personal identification using footstep detection’. Proc. of Int. Symp. on Intelligent Signal Processing and Communication Systems, 2004, pp. 43–47.
18. 18)
  - 5. Wang, X., Yang, T.F., Yao, Y., et al: ‘Footstep identification system based on walking interval’, IEEE Intell. Syst., 2015, 30, pp. 46–52, doi: 10.1109/MIS.2015.5.
19. 19)
  - 3. Kong, A., Zhang, D., Kamel, M.: ‘A survey of palmprint recognition’, Pattern Recognit., 2009, 42, pp. 1408–1418.
20. 20)
  - 7. Reza, J.A., Kossar, J.S., Fariborz, M.: ‘A new illumination invariant feature based on SIFT descriptor in color space’, Procedia Eng., 2012, 41, pp. 305–311.
21. 21)
  - 20. Vera-Rodriguez, R., Mason, J.S.D., Evans, N.W.D.: ‘Assessment of a footstep biometric verification system’ (Advances in Pattern Recognition: Handbook of Remote Biometrics, Springer, 2009), pp. 313–327.
22. 22)
  - 22. Ren, J.: ‘ANN vs. SVM: which one performs better in classification of MCCs in mammogram imaging’, Knowl.-Based Syst., 2012, 26, (1), pp. 144–153.

Robust footstep identification system based on acoustic local features

References

Related content