Abstract
Since multi-target activity recognition solutions based on wearable devices require that sensors be worn at all times, as well as vision-based multi-target activity recognition solutions are susceptible to weather or lighting conditions and are prone to revealing personal privacy, so this paper proposes a real-time multi-target activity recognition solution based on FMCW (Frequency Modulated Continuous Wave) radar to realize non-contact real-time multi-target activity recognition. Firstly, the point cloud data collected by FMCW radar are preprocessed. Secondly, each target information is obtained by multi-target tracking algorithm, and the activity key points and activity feature are extracted. Thirdly, according to the activity characteristic quantity, the data is classified by the classifier to realize the indoor real-time multi-target activity recognition. The test results show that the real-time activity recognition accuracy of this solution for falling, sitting and walking can reach 100%, 87.2% and 100%, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Park, S., Aggarwal, J.: Recognition of two-person interactions using a hierarchical Bayesian network. In: First ACM SIGMM International Workshop on Video Surveillance, pp. 65–76 (2003)
Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 221–231 (2012)
Li, T., Fan, L., Zhao, M., Liu, Y., Katabi, D.: Making the invisible visible: Action recognition through walls and occlusions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 872–881 (2019)
Banerjee, D., et al.: Application of spiking neural networks for action recognition from radar data. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–10. IEEE (2020)
Park, J., Cho, S.H.: IR-UWB radar sensor for human gesture recognition by using machine learning. In: 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 1246–1249. IEEE (2016)
Vandersmissen, B., et al.: Indoor person identification using a low-power FMCW radar. IEEE Trans. Geosci. Remote Sens. 56, 3941–3952 (2018)
Chuma, E.L., Roger, L.L.B., de Oliveira, G.G., Iano, Y., Pajuelo, D.: Internet of Things (IoT) privacy–protected, fall-detection system for the elderly using the radar sensors and deep learning. In: 2020 IEEE International Smart Cities Conference (ISC2), pp. 1–4. IEEE (2020)
Li, H., et al.: Multisensor data fusion for human activities classification and fall detection. In: 2017 IEEE SENSORS, pp. 1–3. IEEE (2017)
Luo, D., Du, S., Ikenaga, T.: Multi-task and multi-level detection neural network based real-time 3D pose estimation. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1427–1434. IEEE (2019)
Ugolotti, R., Sassi, F., Mordonini, M., Cagnoni, S.: Multi-sensor system for detection and classification of human activities. J. Ambient Intell. Humanized Comput. 4, 27–41 (2013)
Will, C., Vaishnav, P., Chakraborty, A., Santra, A.: Human target detection, tracking, and classification using 24-GHz FMCW radar. J. IEEE Sens. J. 19, 7283–7299 (2019)
Ren, A., Wang, Y., Yang, X., Zhou, M.: A dynamic continuous hand gesture detection and recognition method with FMCW radar. In: 2020 IEEE/CIC International Conference on Communications in China (ICCC), pp. 1208–1213. IEEE (2020)
Chen, M.-C., Wu, H.-Y.: Design of a fall detection system. In: 2011 International Conference on Electric Information and Control Engineering, pp. 3148–3151. IEEE (2011)
Livshitz, M.: Tracking radar targets with multiple reflection points. J. TI Internal Document (2017)
Baird, Z., Rajan, S., Bolic, M.: Classification of human posture from radar returns using ultra-wideband radar. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3268–3271. IEEE (2018)
Acknowledgements
This work was supported by the Provincial Natural Science Foundation of Zhejiang (Y21F010057).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pan, H., Liu, K., Shen, L., Tan, A. (2021). Real-Time Multi-target Activity Recognition Based on FMCW Radar. In: Han, Q., McLoone, S., Peng, C., Zhang, B. (eds) Intelligent Equipment, Robots, and Vehicles. LSMS ICSEE 2021 2021. Communications in Computer and Information Science, vol 1469. Springer, Singapore. https://doi.org/10.1007/978-981-16-7213-2_43
Download citation
DOI: https://doi.org/10.1007/978-981-16-7213-2_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7212-5
Online ISBN: 978-981-16-7213-2
eBook Packages: Computer ScienceComputer Science (R0)