Advertisement

Evolving Systems

, Volume 9, Issue 2, pp 135–144 | Cite as

Multistatic radar classification of armed vs unarmed personnel using neural networks

  • Jarez S. Patel
  • Francesco Fioranelli
  • Matthew Ritchie
  • Hugh Griffiths
Original Paper
  • 156 Downloads

Abstract

This paper investigates an implementation of an array of distributed neural networks, operating together to classify between unarmed and potentially armed personnel in areas under surveillance using ground based radar. Experimental data collected by the University College London (UCL) multistatic radar system NetRAD is analysed. Neural networks are applied to the extracted micro-Doppler data in order to classify between the two scenarios, and accuracy above 98% is demonstrated on the validation data, showing an improvement over methodologies based on classifiers where human intervention is required. The main advantage of using neural networks is the ability to bypass the manual extraction process of handcrafted features from the radar data, where thresholds and parameters need to be tuned by human operators. Different network architectures are explored, from feed-forward networks to stacked auto-encoders, with the advantages of deep topologies being capable of classifying the spectrograms (Doppler-time patterns) directly. Significant parameters concerning the actual deployment of the networks are also investigated, for example the dwell time (i.e. how long the radar needs to focus on a target in order to achieve classification), and the robustness of the networks in classifying data from new people, whose signatures were unseen during the training stage. Finally, a data ensembling technique is also presented which utilises a weighted decision approach, established beforehand, utilising information from all three sensors, and yielding stable classification accuracies of 99% or more, across all monitored zones.

Keywords

Multistatic radar Classification Deep neural networks Auto-encoders Micro-Doppler Data ensembling 

Notes

Acknowledgements

This work has been funded by the IET A. F. Harvey Prize awarded to Hugh Griffiths (2013), and by the UK Engineering and Physical Sciences Research Council (EPSRC) which funded Jarez S. Patel for his internship (2015).

References

  1. Chen VC, Tahmoush D, Miceli WL (2014) Radar micro-Doppler signatures: processing and applications. Institution of Engineering and Technology (IET), StevenageCrossRefGoogle Scholar
  2. Derham TE, Doughty S, Woodbridge K, Baker CJ (2007) Design and evaluation of a low-cost multistatic netted radar system. IET Radar Sonar Navig 1(5):362–368CrossRefGoogle Scholar
  3. Doughty SR (2007) Development and performance evaluation of a multistatic radar system. Ph.D. dissertation, University College LondonGoogle Scholar
  4. Fioranelli F, Ritchie M, Griffiths H (2015a) Multistatic human micro-doppler classification of armed/unarmed personnel. IET Radar Sonar Navig 9(7):857–865CrossRefGoogle Scholar
  5. Fioranelli F, Ritchie M, Griffiths H (2015b) Aspect angle dependence and multistatic data fusion for micro-Doppler classification of armed/unarmed personnel. IET Radar Sonar Navig 9(9):1231–1239CrossRefGoogle Scholar
  6. Fioranelli F, Ritchie M, Griffiths H (2016) Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro-Doppler. IET Radar Sonar Navig 10(9):1702–1710CrossRefGoogle Scholar
  7. Haykin S (2006) Cognitive radar: a way of the future. IEEE Signal Process Mag 23(1):30–40CrossRefGoogle Scholar
  8. Haykin S (2008) Neural networks and learning machines: a comprehensive foundation, 3rd edn. Pearson Prentice Hall, Upper Saddle RiverGoogle Scholar
  9. Jordan TS (2016) Using convolutional neural networks for human activity classification on micro-Doppler radar spectrograms. in: Proceedings SPIE, vol 9825Google Scholar
  10. Jokanovic B, Amin M, Ahmad F (2016a) Radar fall motion detection using deep learning. In: 2016 IEEE radar conference (RadarConf), p 16Google Scholar
  11. Jokanovic B, Amin M, Ahmad F (2016b) Effect of data representations on deep learning in fall detection. In: IEEE sensor array and multichannel signal processing workshop (SAM), p 15Google Scholar
  12. Jokanovic B, Amin M, Erol B (2017) Multiple joint-variable domains recognition of human motion. In: 2017 IEEE radar conference, SeattleGoogle Scholar
  13. Kwon J, Kwak N (2017) Human detection by neural networks using a low-cost short-range Doppler radar sensor. In: 2017 IEEE radar conference, SeattleGoogle Scholar
  14. Seyfioglu Seyfioglu M, Gurbuz S, Ozbayoglu A, Yuksel M (2017) Deep learning of micro-Doppler features for aided and unaided gait recognition. In: 2017 IEEE radar conference, SeattleGoogle Scholar
  15. Stimson GW, Griffiths HD, Baker CJ, Adamy D (2014) Stimsons Introduction to airborne radar, 3rd edn. SciTech (IET), StevenageGoogle Scholar
  16. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  17. Park J, Javier RJ, Moon T, Kim Y (2016) Micro-Doppler based classification of human aquatic activities via transfer learning of convolutional neural networks. Sensors 16(12):2016CrossRefGoogle Scholar
  18. Parashar K, Oveneke M, Rykunov M, Sahli M, Bourdoux A (2017) Micro-Doppler feature extraction using convolutional auto-encoders for low latency classification. In :IEEE radar conference, SeattleGoogle Scholar
  19. Tahmoush D, Silvious J (2009a) Radar microDoppler for security applications: modelling men versus women. In: IEEE Antennas and Propagation Society international symposium, APSURSI, Charleston, SC, USA, pp 1–4, 1–5Google Scholar
  20. Tahmoush D, Silvious J (2009b) Remote detection of humans and animals. In: IEEE applied imagery pattern recognition workshop (AIPRW), 14–16 October, Washington DC, pp 1–8Google Scholar
  21. Tivive F, Bouzerdoum A, Amin M (2010) A human gait classification method based on radar Doppler spectrograms. EURASIP J Adv Signal Process 2010:389716Google Scholar
  22. Youngwook K, Hao L (2008) Human activity classification based on micro-Doppler signatures using an artificial neural network. In: IEEE Antennas and Propagation Society international symposium, San Diego, pp 1–4Google Scholar
  23. Youngwook K, Hao L (2009) Human activity classification based on micro-Doppler signatures using a support vector machine. IEEE Trans Geosci Remote Sens 47(5):1328–1337CrossRefGoogle Scholar
  24. Youngwook K, Sungjae H, Jihoon K (2015) Human detection using Doppler radar based on physical characteristics of targets. IEEE Geosci Remote Sens Lett 12(2):289–293CrossRefGoogle Scholar
  25. Youngwook K, Moon T (2016) Human detection and activity classification based on micro-Doppler signatures using deep convolutional neural networks. IEEE Geosci Remote Sens Lett 13(1):8–12CrossRefGoogle Scholar
  26. Youngwook K, Toomajian B (2016) Hand Gesture recognition using micro-Doppler signatures with convolutional neural network. IEEE Access 4:7125–7130Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  1. 1.University College LondonLondonUK
  2. 2.University of GlasgowGlasgowUK

Personalised recommendations