Abstract
Deep convolution neural networks (DCNN) have been an excellent classifier in various fields such as radar images classification. However, the number of training samples deeply influences the performance of networks and radar samples are not easy to be obtained. In this paper, we utilize micro-Doppler simulated data from Kinect sensor and online dataset to train networks and figure out the differences. In order to enhance the reliability of Kinect simulation, a filter for Kinect data is proposed. Later, transfer learning is used to improve the performance. Moreover, bistatic deep convolutional neural networks (bistatic-DCNN) are proposed. After transfer learning, experimental results show that the performances of both 7-class and 13-class motion classification reach over 98%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, V.C.: Analysis of radar micro-Doppler with time-frequency transform. Proc. Statistical Signal Array Processing, USA, pp. 463–466 (2020)
Chen, V.C., Li, F., Ho, S.-S., et al.: Analysis of micro-Doppler signatures. IEEE Proceedings—Radar, Sonar Navig. 150(4), 271–276 (2003)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nat. 521, 436–444 (2015)
Kim, Y., Moon, T.: Human detection and activity classification based on microDoppler signatures using deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 413(1), 8–12 (2016)
Shao, Y., Dai, Y., Yuan, L., et al.: Deep learning methods for personnel recognition based on micro-Doppler features. In: Proceedings 9th International Conference on Signal Processing Systems (ICSPS), ACM, pp. 94–98 (2017)
Chen, Z., Li, G., Fioranelli, F., et al.: Personnel recognition and Gait classification based on multi static micro-doppler signatures using deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 15(5), 1–5 (2018)
Seyfioğlu, M.S., Özbayoğlu, A.M., Gürbüz, S.Z.: Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities. IEEE Trans. Aerospace Elect. Syst. 54(4), 1709–1723 (2018)
Alnujaim, I., Oh, D., Kim, Y.: Generative adversarial networks for classification of micro-Doppler signatures of human activity. IEEE Geosci. Remote Sens. Lett. 17(3), 396–400 (2019)
Park, J., Rios, R.J., Moon, T., et al.: Micro-Doppler based classification of human aquatic activities via transfer learning of convolutional neural networks. Sensors 16(12), 1990 (2016)
Erol, B., Karabacak, C., et al..: Simulation of human micro-Doppler signatures with kinect sensor. In: 2014 IEEE Radar Conference, pp. 0863–0868 (2014)
Carnegie Mellon University, Graphics Laboratory Motion Capture Database [Online], PA, USA: http://mocap.cs.cmu.edu/
Karabacak, C., Gurbuz, S.Z., Gurbuz, A.C., et al.: Knowledge exploitation for Human Micro-Doppler classification. IEEE Geosci. Remote Sens. Lett. 12(10), 2125–2129 (2015)
Seyfioglu, M.S., Erol, B., Gurbuz, S.Z., et al.: Diversified radar micro-Doppler simulations as training data for deep residual neural networks. in IEEE Radar Conference, USA, pp. 612–617 (2018)
Andersen, N., Granhaug, K., Michaelsen, J.A., et al.: A 118-mW pulse-based Radar SoC in 55-nm CMOS for non-contact human vital signs detection. IEEE J. Solid-State Circuits 52(12), 3421–3433 (2017)
Piccardi, M.: Background subtraction techniques: a review. In: 2004 IEEE International Conference on Systems, 4, pp. 3099–3104 (2014)
Boulic, R., Thalmann, N.M., Thalmann, D.: A global walking model with real-time kinematic personification. The Visual Comp. 6, 344–358 (1990)
Huang, G., Liu, Z., Weinberger, K.Q., et al.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017)
Acknowledgements
This work was supported in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2019A1515011517, in part by the Science and Technology Project of Shenzhen under Grant JCYJ20190808142803565, and in part by the National Natural Science Foundation of China under Grant 62101207.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lai, J., Chu, P., Yang, Z. (2023). Human Activity Classification Based-On Micro-Doppler Simulations with DNNs and Transfer Learning. In: Dong, J., Zhang, L. (eds) Proceedings of the International Conference on Internet of Things, Communication and Intelligent Technology . IoTCIT 2022. Lecture Notes in Electrical Engineering, vol 1015. Springer, Singapore. https://doi.org/10.1007/978-981-99-0416-7_50
Download citation
DOI: https://doi.org/10.1007/978-981-99-0416-7_50
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0415-0
Online ISBN: 978-981-99-0416-7
eBook Packages: EngineeringEngineering (R0)