Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar
Doppler-radar-based continuous human motion recognition recently has attracted extensive attention, which is a favorable choice for privacy and personal security. Existing results of continuous human motion recognition (CHMR) using mmWave FMCW Radar are not considered the continuous human motion wit...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/21/8409 |
_version_ | 1797466468676272128 |
---|---|
author | Yuh-Shyan Chen Kuang-Hung Cheng You-An Xu Tong-Ying Juang |
author_facet | Yuh-Shyan Chen Kuang-Hung Cheng You-An Xu Tong-Ying Juang |
author_sort | Yuh-Shyan Chen |
collection | DOAJ |
description | Doppler-radar-based continuous human motion recognition recently has attracted extensive attention, which is a favorable choice for privacy and personal security. Existing results of continuous human motion recognition (CHMR) using mmWave FMCW Radar are not considered the continuous human motion with the high similarity problem. In this paper, we proposed a new CHMR algorithm with the consideration of the high similarity (HS) problem, called as CHMR-HS, by using the modified Transformer-based learning model. As far as we know, this is the first result in the literature to investigate the continuous HMR with the high similarity. To obtain the clear FMCW radar images, the background and target signals of the detected human are separated through the background denoising and the target extraction algorithms. To investigate the effects of the spectral-temporal multi-features with different dimensions, Doppler, range, and angle signatures are extracted as the 2D features and range-Doppler-time and range-angle-time signatures are extracted as the 3D features. The 2D/3D features are trained into the adjusted Transformer-encoder model to distinguish the difference of the high-similarity human motions. The conventional Transformer-decoder model is also re-designed to be Transformer-sequential-decoder model such that Transformer-sequential-decoder model can successfully recognize the continuous human motions with the high similarity. The experimental results show that the accuracy of our proposed CHMR-HS scheme are 95.2% and 94.5% if using 3D and 2D features, the simulation results also illustrates that our CHMR-HS scheme has advantages over existing CHMR schemes. |
first_indexed | 2024-03-09T18:40:17Z |
format | Article |
id | doaj.art-9ec1c5f74d354ca1ba5a28cb9c41e325 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T18:40:17Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-9ec1c5f74d354ca1ba5a28cb9c41e3252023-11-24T06:47:37ZengMDPI AGSensors1424-82202022-11-012221840910.3390/s22218409Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW RadarYuh-Shyan Chen0Kuang-Hung Cheng1You-An Xu2Tong-Ying Juang3Department of Computer Science and Information Engineering, National Taipei University, No. 151, University Rd., San Shia District, New Taipei City 23741, TaiwanDepartment of Computer Science and Information Engineering, National Taipei University, No. 151, University Rd., San Shia District, New Taipei City 23741, TaiwanDepartment of Computer Science and Information Engineering, National Taipei University, No. 151, University Rd., San Shia District, New Taipei City 23741, TaiwanDepartment of Computer Science and Information Engineering, National Taipei University, No. 151, University Rd., San Shia District, New Taipei City 23741, TaiwanDoppler-radar-based continuous human motion recognition recently has attracted extensive attention, which is a favorable choice for privacy and personal security. Existing results of continuous human motion recognition (CHMR) using mmWave FMCW Radar are not considered the continuous human motion with the high similarity problem. In this paper, we proposed a new CHMR algorithm with the consideration of the high similarity (HS) problem, called as CHMR-HS, by using the modified Transformer-based learning model. As far as we know, this is the first result in the literature to investigate the continuous HMR with the high similarity. To obtain the clear FMCW radar images, the background and target signals of the detected human are separated through the background denoising and the target extraction algorithms. To investigate the effects of the spectral-temporal multi-features with different dimensions, Doppler, range, and angle signatures are extracted as the 2D features and range-Doppler-time and range-angle-time signatures are extracted as the 3D features. The 2D/3D features are trained into the adjusted Transformer-encoder model to distinguish the difference of the high-similarity human motions. The conventional Transformer-decoder model is also re-designed to be Transformer-sequential-decoder model such that Transformer-sequential-decoder model can successfully recognize the continuous human motions with the high similarity. The experimental results show that the accuracy of our proposed CHMR-HS scheme are 95.2% and 94.5% if using 3D and 2D features, the simulation results also illustrates that our CHMR-HS scheme has advantages over existing CHMR schemes.https://www.mdpi.com/1424-8220/22/21/8409FMCWcontinuous human motion recognitionhigh similaritymulti-featureTransformer |
spellingShingle | Yuh-Shyan Chen Kuang-Hung Cheng You-An Xu Tong-Ying Juang Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar Sensors FMCW continuous human motion recognition high similarity multi-feature Transformer |
title | Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar |
title_full | Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar |
title_fullStr | Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar |
title_full_unstemmed | Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar |
title_short | Multi-Feature Transformer-Based Learning for Continuous Human Motion Recognition with High Similarity Using mmWave FMCW Radar |
title_sort | multi feature transformer based learning for continuous human motion recognition with high similarity using mmwave fmcw radar |
topic | FMCW continuous human motion recognition high similarity multi-feature Transformer |
url | https://www.mdpi.com/1424-8220/22/21/8409 |
work_keys_str_mv | AT yuhshyanchen multifeaturetransformerbasedlearningforcontinuoushumanmotionrecognitionwithhighsimilarityusingmmwavefmcwradar AT kuanghungcheng multifeaturetransformerbasedlearningforcontinuoushumanmotionrecognitionwithhighsimilarityusingmmwavefmcwradar AT youanxu multifeaturetransformerbasedlearningforcontinuoushumanmotionrecognitionwithhighsimilarityusingmmwavefmcwradar AT tongyingjuang multifeaturetransformerbasedlearningforcontinuoushumanmotionrecognitionwithhighsimilarityusingmmwavefmcwradar |