Advertisement

Threat Identification in Humanitarian Demining Using Machine Learning and Spectroscopic Metal Detection

  • Wouter van VerreEmail author
  • Toykan Özdeǧer
  • Ananya Gupta
  • Frank J. W. Podd
  • Anthony J. Peyton
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11871)

Abstract

The detection of buried minimum-metal anti-personnel landmines is a time-consuming problem, due to the high false alarm rate (FAR) arising from metallic clutter typically found in minefields. Magnetic induction spectroscopy (MIS) offers a potential way to reduce the FAR by classifying the metallic objects into threat and non-threat categories, based on their spectroscopic signatures. A new algorithm for threat identification for MIS sensors, based on a fully-connected artificial neural network (ANN), is proposed in this paper, and compared against a classifier based on Support Vector Machines (SVM). The results demonstrate that MIS is a potentially viable option for the reduction of false alarms in humanitarian demining. It is also shown that the ANN outperforms the SVM-based approach for threat objects containing minimal amounts of metal.

Keywords

Magnetic induction spectroscopy Machine learning Landmine detection 

References

  1. 1.
    Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/
  2. 2.
    Amazeen, C., Locke, M.: Developmental status of the U.S. Army’s new Handheld STAndoff MIne Detection System (HSTAMIDS). In: Second International Conference on Detection of Abandoned Land Mines, vol. 1998, pp. 193–197 (1998)Google Scholar
  3. 3.
    Chollet, F., et al.: Keras (2015). https://keras.io
  4. 4.
    Daniels, D., Braustein, J., Nevard, M.: Using MINEHOUND in Cambodia and Afghanistan. J. ERW Mine Action 18(2), 14 (2014)Google Scholar
  5. 5.
    Daniels, D.J.: A review of GPR for landmine detection. Sens. Imaging: Int. J. 7(3), 90–123 (2006)CrossRefGoogle Scholar
  6. 6.
    Geophex: GEM-3M: A Ground Imager with a Local Navigator. Technical report (2012)Google Scholar
  7. 7.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
  8. 8.
    Huang, H., Won, I.J.: Automated identification of buried landmines using normalized electromagnetic induction spectroscopy. IEEE Trans. Geosci. Remote Sens. 41(3), 640–651 (2003)CrossRefGoogle Scholar
  9. 9.
    Huang, H., Won, I.J.: Characterization of UXO-like targets using broadband electromagnetic induction sensors. IEEE Trans. Geosci. Remote Sens. 41(3), 652–663 (2003)CrossRefGoogle Scholar
  10. 10.
    Knox, M., Rundel, C., Collins, L.: Sensor fusion for buried explosive threat detection for handheld data. In: Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII 10182, May 2017. 101820D (2017).  https://doi.org/10.1117/12.2263013
  11. 11.
    Lameri, S., Lombardi, F., Bestagini, P., Lualdi, M., Tubaro, S.: Landmine detection from GPR data using convolutional neural networks. In: 25th European Signal Processing Conference, EUSIPCO, January 2017, pp. 508–512 (2017).  https://doi.org/10.23919/EUSIPCO.2017.8081259
  12. 12.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)CrossRefGoogle Scholar
  13. 13.
    Marsh, L.A., et al.: Spectroscopic identification of anti-personnel mine surrogates from planar sensor measurements. In: Proceedings of IEEE Sensors, pp. 1–3 (2016)Google Scholar
  14. 14.
    Marsh, L.A., et al.: Combining electromagnetic spectroscopy and ground-penetrating radar for the detection of anti-personnel landmines. Sensors 19(15), 3390 (2019)CrossRefGoogle Scholar
  15. 15.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Sato, M., Kikuta, K., Chernyak, I.: Dual sensor “ALIS” for humanitarian demining. In: 2018 17th International Conference on Ground Penetrating Radar (GPR), pp. 1–4 (2018)Google Scholar
  17. 17.
    Stanley, R.J., Gader, P.D., Ho, K.C.: Feature and decision level sensor fusion of electromagnetic induction and ground penetrating radar sensors for landmine detection with hand-held units (2002)CrossRefGoogle Scholar
  18. 18.
    The Halo Trust: HALO Utilises Dual-sensor Detector | The HALO Trust (2011). https://www.halotrust.org/media-centre/news/halo-utilises-dual-sensor-detector/
  19. 19.
    UN Secretary General: Assistance in mine clearance: Report of the Secretary-General A/49/357. Technical report, United Nations, September 1994Google Scholar
  20. 20.
    van Verre, W., Marsh, L.A., Davidson, J.L., Cheadle, E., Podd, F.J.W., Peyton, A.J.: Detection of Metallic Objects in Mineralised Soil Using Magnetic Induction Spectroscopy (2019, submitted)Google Scholar
  21. 21.
    Won, I.J., Keiswetter, D.A., Bell, T.H., Miller, J., Barrow, B.: Electromagnetic induction spectroscopy for landmine identification. IEEE Trans. Geosci. Remote Sens. 39(4), 801–809 (2001)CrossRefGoogle Scholar
  22. 22.
    Won, I.J., Keiswetter, D.A., Hanson, D.R., Novikova, E., Hall, T.M.: GEM-3: Monostatic Broadband Electromagnetic Induction Sensor (1997)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of ManchesterManchesterUK

Personalised recommendations