Gunshot Classification from Single-channel Audio Recordings using a Divide and Conquer Approach

Héctor A. Sánchez-Hevia, David Ayllón, Roberto Gil-Pita, Manuel Rosa-zurera

2015

Abstract

Gunshot acoustic analysis is a field with many practical applications, but due to the multitude of factors involved in the generation of the acoustic signature of firearms, it is not a trivial task, especially since the recorded waveforms show a strong dependence on the shooter’s position and orientation, even when firing the same weapon. In this paper we address acoustic weapon classification using pattern recognition techniques with single channel recordings while taking into account the spatial aspect of the problem, so departing from the typical approach. We are working with three broad categories: rifles, handguns and shotguns. Our approach is based on two proposals: a Divide and Conquer classification strategy and the inclusion of some novel features based on the physical model of gunshot acoustics. The Divide and Conquer strategy is aimed at improving the rate of success of the classification stage by using previously retrieved spatial information to select between a set of specialized weapon classifiers. The minimum relative error reduction achieved when both proposals are used, compared with a single-stage classifier employing traditional features is 38.7%.

References

  1. Ahmed, T., Uppal, M., and Muhammad, A. (2013). Improving efficiency and reliability of gunshot detection systems. In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pages 513-517. IEEE.
  2. Efron, B. (1979). Bootstrap methods: another look at the jackknife. The annals of Statistics, pages 1-26.
  3. Fansler, K. S., Thompson, W. P., Carnahan, J. S., and Patton, B. J. (1993). A parametric investigation of muzzle blast. Technical report, DTIC Document.
  4. Freire, I. L. and Apolinário Jr, J. A. (2010). Gunshot detection in noisy environments. In Proceeding of the 7th International Telecommunications Symposium, Manaus, Brazil.
  5. Freytaga, J. C., Begaultb, D. R., and Peltierc, C. A. (2006). The acoustics of gunfire. In INTER-NOISE.
  6. Hunt, M., Lennig, M., and Mermelstein, P. (1980). Experiments in syllable-based recognition of continuous speech. In Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'80., volume 5, pages 880-883. IEEE.
  7. ISO-CEN.17201-2 (2006). Acoustics noise from shooting ranges part 2: Estimation of muzzle blast and projectile sound by calculation.
  8. Karl Wilhem Hirsch, W. B. (2013). Estimation of the directivity pattern of muzzle blasts. In AIA-DAGA.
  9. Kawalec, A., Pietrasinski, J., and Danicki, E. (2006). Selected problems of sniper acoustic localization. Technical report, DTIC Document.
  10. Khan, S., Divakaran, A., and Sawhney, H. S. (2009). Weapon identification using hierarchical classification of acoustic signatures. In SPIE Defense, Security, and Sensing, pages 730510-730510. International Society for Optics and Photonics.
  11. Maher, R. (2006). Modeling and signal processing of acoustic gunshot recordings. In Digital Signal Processing Workshop, 12th-Signal Processing Education Workshop, 4th, pages 257-261. IEEE.
  12. Maher, R. C. (2007). Acoustical characterization of gunshots. Proc. SAFE 2007 (Washington, DC, IEEE Signal Processing Society, 11-13 April 2007), pages 109-113.
  13. Maher, R. C. and Shaw, S. R. (2010). Directional aspects of forensic gunshot recordings. In Audio Engineering Society Conference: 39th International Conference: Audio Forensics: Practices and Challenges. Audio Engineering Society.
  14. Millet, J. and Baligand, B. (2006). Latest achievements in gunfire detection systems. Technical report, DTIC Document.
  15. Parvin, H., Alinejad-Rokny, H., and Parvin, S. (2011). Divide and conquer classification. Australian Journal of Basic & Applied Sciences, 5(12).
  16. Sallai, J., Hedgecock, W., Volgyesi, P., Nadas, A., Balogh, G., and Ledeczi, A. (2011). Weapon classification and shooter localization using distributed multichannel acoustic sensors. Journal of Systems Architecture, 57(10):869-885.
  17. Sergent, E. W. and Winkler, J. C. (1995). Gunshot detector. US Patent 5,455,868.
  18. Weissler, P. G. and Kobal, M. T. (1974). Noise of police firearms. The Journal of the Acoustical Society of America, 56(5):1515-1522.
  19. Ye, J. (2007). Least squares linear discriminant analysis. In Proceedings of the 24th international conference on Machine learning, pages 1087-1093. ACM.
Download


Paper Citation


in Harvard Style

Sánchez-Hevia H., Ayllón D., Gil-Pita R. and Rosa-zurera M. (2015). Gunshot Classification from Single-channel Audio Recordings using a Divide and Conquer Approach . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-758-077-2, pages 233-240. DOI: 10.5220/0005218302330240


in Bibtex Style

@conference{icpram15,
author={Héctor A. Sánchez-Hevia and David Ayllón and Roberto Gil-Pita and Manuel Rosa-zurera},
title={Gunshot Classification from Single-channel Audio Recordings using a Divide and Conquer Approach},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2015},
pages={233-240},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005218302330240},
isbn={978-989-758-077-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - Gunshot Classification from Single-channel Audio Recordings using a Divide and Conquer Approach
SN - 978-989-758-077-2
AU - Sánchez-Hevia H.
AU - Ayllón D.
AU - Gil-Pita R.
AU - Rosa-zurera M.
PY - 2015
SP - 233
EP - 240
DO - 10.5220/0005218302330240