Radar-Based Human Activity Recognition Under the Limited Measurement Data Support Using Domain Translation
- 19 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 1993-1997
Abstract
In recent years, radar-based human activity recognition has received considerable interest, but it faces the difficulty of a shortage of training data. In this research, a two-stage domain adaption method is proposed for this issue. This method combines simulated radar spectrograms with an elaborated domain-translation network to perform domain adaptation, hence enabling human activity recognition with limited measurement data support. To validate the efficacy of our method, we conduct radar simulation and measurements, and the experimental results demonstrate that the proposed method outperforms other comparisons in terms of accuracy, showing its great capacity for radar-based human activity recognition.Keywords
Funding Information
- National Key R&D Program of China (2021YFE0204200)
- National Natural Science Foundation of China (62171318, 62101378)
This publication has 21 references indexed in Scilit:
- Abnormal gait detection and classification using micro-Doppler radar signatures2019
- Toward Unobtrusive In-Home Gait Analysis Based on Radar Micro-Doppler SignaturesIEEE Transactions on Biomedical Engineering, 2019
- Hand-Gesture Recognition Using Two-Antenna Doppler Radar With Deep Convolutional Neural NetworksIEEE Sensors Journal, 2019
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Application of Doppler radar for the recognition of hand gestures using optimized deep convolutional neural networks2017
- Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural NetworksSensors, 2016
- Fast R-CNN2015
- Range‐Doppler surface: a tool to analyse human target in ultra‐wideband radarIET Radar, Sonar & Navigation, 2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Integrating structured biological data by Kernel Maximum Mean DiscrepancyBioinformatics, 2006