Abstract
This paper reports a machine learning approach for people detection and tracking in indoor environments using a compact radar system deployed by a mobile robot. The set-up described in the paper includes a series of experiments carried out in an indoor scenario involving walking people and dummies representative of other moving objects. In these experiments, distinct learning models (a neural network and a random forest) were explored with different combinations of radar features to achieve person versus non-person classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barrett, D., Alvarez, A.: mmWave radar sensors in robotics applications. Technical report, Texas Instruments (2017)
Berkius, C., Buck, M., Gustafsson, J., Kauppinen, M.: Human control of mobile robots using hand gestures. Bachelor thesis in electrical engineering, Chalmers University of Technology. Gothenburg, Sweden (2018)
Dogru, S., Marques, L.: Using radar for grid-based indoor mapping. In: Proceedings of the 19th IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2019, Gondomar, Porto, Portugal, 24–25 April 2019
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, KDD 1996, pp. 226–231. AAAI Press (1996)
Gurbuz, S.Z., Amin, M.G.: Radar-based human-motion recognition with deep learning: promising applications for indoor monitoring. IEEE Signal Process. Mag. 36(4), 16–28 (2019). https://doi.org/10.1109/MSP.2018.2890128
Heuel, S., Rohling, H.: Pedestrian recognition based on 24 GHz radar sensors. Ultra-Wideband Radio Technologies for Communications, Localization and Sensor Applications, chap. 10, pp. 241–256. InTech (2013)
Knudde, N., Vandersmissen, B., Parashar, K., Couckuyt, I., Jalalvand, A., Bourdoux, A., Neve, W.D., Dhaene, T.: Indoor tracking of multiple persons with a 77 GHz MIMO FMCW radar. In: 2017 European Radar Conference (EURAD), pp. 61–64 (2017)
Livshitz, M.: Tracking radar targets with multiple reflection points (2018). https://e2e.ti.com/cfs-file/__key/communityserver-discussions-components-files/1023/Tracking-radar-targets-with-multiple-reflection-points.pdf. Accessed 13 June 2019
Machado, S., Mancheno, S.: Automotive FMCW radar development and verification methods. Master’s thesis, Department of Computer Science and Engineering. Chalmers University of Technology. University of Gothenburg, Sweden (2018)
Takeuchi, E., Elfes, A., Roberts, J.: Localization and Place Recognition Using an Ultra-Wide Band (UWB) Radar. Springer Tracts in Advanced Robotics, vol. 105. Springer (2015)
Texas-Instruments: People Tracking and Counting Reference Design Using mmWave Radar Sensor. TI Designs: TIDEP-01000, March 2018
Yamada, H., Wakamatsu, Y., Sato, K., Yamaguchi, Y.: Indoor human detection by using Quasi-MIMO doppler radar. In: 2015 International Workshop on Antenna Technology (iWAT), pp. 35–38 (2015)
Acknowledgement
This work is funded by Research Project RETIOT PT2020-03/SAICT/2015 - Fundação para a Ciência e Tecnologia.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Castanheira, J., Curado, F., Pedrosa, E., Gonçalves, E., Tomé, A. (2020). Machine Learning Methods for Radar-Based People Detection and Tracking by Mobile Robots. In: Silva, M., Luís Lima, J., Reis, L., Sanfeliu, A., Tardioli, D. (eds) Robot 2019: Fourth Iberian Robotics Conference. ROBOT 2019. Advances in Intelligent Systems and Computing, vol 1093. Springer, Cham. https://doi.org/10.1007/978-3-030-36150-1_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-36150-1_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36149-5
Online ISBN: 978-3-030-36150-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)