Skip to main content

Unveiling the Potential of Tiny Machine Learning for Enhanced People Counting in UWB Radar Data

  • Conference paper
  • First Online:
Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2023)

Abstract

Tiny Machine Learning (TinyML) allows to move the intelligence processing as close as possible to where data are generated, hence reducing the latency with which a decision is made and being able to process data even when remote connection is scarce or absent. In this technological scenario, Ultra-Wideband (UWB) radar data represent a new and challenging source of data providing relevant information, while guaranteeing the privacy of users. This paper introduces a novel TinyML solution able to count the number of people in a given area by processing UWB radar data. This novel solution was carefully designed to guarantee a high counting accuracy, while reducing the memory and computational demand so as to be executed on tiny devices. Experimental results on a real-world UWB radar dataset show the effectiveness of the proposed solution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Codecarbon. https://codecarbon.io/. Accessed 30 Sept 2010

  2. Alippi, C., Disabato, S., Roveri, M.: Moving convolutional neural networks to embedded systems: the AlexNet and VGG-16 case. In: 2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), pp. 212–223 (2018). https://doi.org/10.1109/IPSN.2018.00049

  3. Alippi, C., Disabato, S., Roveri, M.: Moving convolutional neural networks to embedded systems: the AlexNet and VGG-16 case. In: 2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), pp. 212–223. IEEE (2018)

    Google Scholar 

  4. Alippi, C., Fantacci, R., Marabissi, D., Roveri, M.: A cloud to the ground: the new frontier of intelligent and autonomous networks of things. IEEE Commun. Mag. 54(12), 14–20 (2016). https://doi.org/10.1109/MCOM.2016.1600541CM

    Article  MATH  Google Scholar 

  5. Alippi, C., Roveri, M.: The (not) far-away path to smart cyber-physical systems: an information-centric framework. Computer 50(4), 38–47 (2017). https://doi.org/10.1109/MC.2017.111

    Article  Google Scholar 

  6. Choi, J.W., Yim, D.H., Cho, S.H.: People counting based on an IR-UWB radar sensor. IEEE Sens. J. 17(17), 5717–5727 (2017). https://doi.org/10.1109/JSEN.2017.2723766

  7. Chowdhery, A., Warden, P., Shlens, J., Howard, A., Rhodes, R.: Visual Wake Words Dataset. arXiv:1906.05721 [cs, eess] (2019). http://arxiv.org/abs/1906.05721, arXiv: 1906.05721

  8. David, R., Duke, J., et al.: TensorFlow lite micro: embedded machine learning for TinyML systems. Proc. Mach. Learn. Syst. 3, 800–811 (2021)

    Google Scholar 

  9. Disabato, S., Roveri, M.: Reducing the computation load of convolutional neural networks through gate classification. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2018)

    Google Scholar 

  10. Ha, T., Kim, J.: Detection and localization of multiple human targets based on respiration measured by IR-UWB radars. In: 2019 IEEE SENSORS, pp. 1–4 (2019). https://doi.org/10.1109/SENSORS43011.2019.8956687. ISSN 2168-9229

  11. Jacob, B., Kligys, S., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704–2713 (2018)

    Google Scholar 

  12. Kim, Y., Moon, T.: Human detection and activity classification based on micro-doppler signatures using deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 13(1), 8–12 (2016). https://doi.org/10.1109/LGRS.2015.2491329

    Article  ADS  MathSciNet  MATH  Google Scholar 

  13. Koks, D.: How to create and manipulate radar range–doppler plots, p. 95 (2014)

    Google Scholar 

  14. Lang, Y., Hou, C., Yang, Y., Huang, D., He, Y.: Convolutional neural network for human micro-doppler classification. In: European Microwave Conference (2017)

    Google Scholar 

  15. Liang, F., et al.: Detection of multiple stationary humans using UWB MIMO radar. Sensors 16, 1922 (2016). https://doi.org/10.3390/s16111922

    Article  ADS  PubMed  PubMed Central  MATH  Google Scholar 

  16. Liu, J., Tripathi, S., Kurup, U., Shah, M.: Pruning algorithms to accelerate convolutional neural networks for edge applications: a survey. arXiv preprint arXiv:2005.04275 (2020)

  17. Louis Moreau, M.K.: Announcing FOMO (faster objects, more objects) (2022). https://www.edgeimpulse.com/blog/announcing-fomo-faster-objects-more-objects

  18. Park, J., Javier, R.J., Moon, T., Kim, Y.: Micro-doppler based classification of human aquatic activities via transfer learning of convolutional neural networks. Sensors 16(12), 1990 (2016). https://doi.org/10.3390/s16121990. https://www.mdpi.com/1424-8220/16/12/1990

  19. Pavan, M., Caltabiano, A., Roveri, M.: On-device subject recognition in UWB-radar data with tiny machine learning. In: CEUR Workshop Proceedings (2022)

    Google Scholar 

  20. Pavan, M., Clatabiano, A., Roveri, M.: TinyML for UWB-radar based presence detection. In: Proceedings of WCCI 2022, p. 5. IEEE, July 2022

    Google Scholar 

  21. Pham, C.T., Luong, V.S., Nguyen, D.K., Vu, H.H.T., Le, M.: Convolutional neural network for people counting using UWB impulse radar. J. Instrum. 16(08), P08031 (2021). https://doi.org/10.1088/1748-0221/16/08/P08031. https://dx.doi.org/10.1088/1748-0221/16/08/P08031

  22. Prakash, S., et al.: Is TinyML sustainable? Assessing the environmental impacts of machine learning on microcontrollers (2023)

    Google Scholar 

  23. Ray, P.P.: A review on TinyML: state-of-the-art and prospects 34(4), 1595–1623 (2022). https://doi.org/10.1016/j.jksuci.2021.11.019. https://www.sciencedirect.com/science/article/pii/S1319157821003335

  24. Sanchez-Iborra, R., Skarmeta, A.F.: TinyML-enabled frugal smart objects: challenges and opportunities. IEEE Circuits Syst. Mag. 20(3), 4–18 (2020)

    Article  MATH  Google Scholar 

  25. Shao, Y., Guo, S., Sun, L., Chen, W.: Human motion classification based on range information with deep convolutional neural network. In: 2017 4th International Conference on Information Science and Control Engineering (ICISCE), pp. 1519–1523 (2017). https://doi.org/10.1109/ICISCE.2017.317

  26. Warden, P.: Speech commands: a dataset for limited-vocabulary speech recognition. arXiv:1804.03209 [cs] (2018). http://arxiv.org/abs/1804.03209, arXiv: 1804.03209

  27. Warden, P., Situnayake, D.: TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-power Microcontrollers. O’Reilly (2020). Google-Books-ID: sB3mxQEACAAJ

    Google Scholar 

  28. Weiß, J., Pérez, R., Biebl, E.: Improved people counting algorithm for indoor environments using 60 GHz FMCW radar. In: 2020 IEEE Radar Conference (RadarConf 2020), pp. 1–6 (2020). https://doi.org/10.1109/RadarConf2043947.2020.9266607. ISSN 2375-5318

  29. Yang, X., Yin, W., Zhang, L.: People counting based on CNN using IR-UWB radar. In: 2017 IEEE/CIC International Conference on Communications in China (ICCC), pp. 1–5 (2017). https://doi.org/10.1109/ICCChina.2017.8330453

  30. Zach: Z-score normalization: definition & examples (2021). https://www.statology.org/z-score-normalization/

Download references

Acknowledgments

The authors would like to thank Gabriele Viscardi, Pierpaolo Lento and Alessandro Basso for the valuable support in the development of this work. This paper is supported by PNRR-PE-AI FAIR project funded by the NextGeneration EU program.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Massimo Pavan .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Pavan, M., Navarro, L.G., Caltabiano, A., Roveri, M. (2025). Unveiling the Potential of Tiny Machine Learning for Enhanced People Counting in UWB Radar Data. In: Meo, R., Silvestri, F. (eds) Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2023. Communications in Computer and Information Science, vol 2136. Springer, Cham. https://doi.org/10.1007/978-3-031-74640-6_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-74640-6_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-74639-0

  • Online ISBN: 978-3-031-74640-6

  • eBook Packages: Artificial Intelligence (R0)

Publish with us

Policies and ethics