A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds
Low-frequency Ultra-WideBand (UWB) radar offers significant advantages in the field of human activity recognition owing to its excellent penetration and resolution. To address the issues of high computational complexity and extensive network parameters in existing action recognition algorithms, this...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Science Publishing & Media Ltd. (CSPM)
2025-02-01
|
| Series: | Leida xuebao |
| Subjects: | |
| Online Access: | https://radars.ac.cn/cn/article/doi/10.12000/JR24110 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591749823856640 |
|---|---|
| author | Yongkun SONG Tianxing YAN Ke ZHANG Xian LIU Yongpeng DAI Tian JIN |
| author_facet | Yongkun SONG Tianxing YAN Ke ZHANG Xian LIU Yongpeng DAI Tian JIN |
| author_sort | Yongkun SONG |
| collection | DOAJ |
| description | Low-frequency Ultra-WideBand (UWB) radar offers significant advantages in the field of human activity recognition owing to its excellent penetration and resolution. To address the issues of high computational complexity and extensive network parameters in existing action recognition algorithms, this study proposes an efficient and lightweight human activity recognition method using UWB radar based on spatiotemporal point clouds. First, four-dimensional motion data of the human body are collected using UWB radar. A discrete sampling method is then employed to convert the radar images into point cloud representations. Because human activity recognition is a classification problem on time series, this paper combines the PointNet++ network with the Transformer network to propose a lightweight spatiotemporal network. By extracting and analyzing the spatiotemporal features of four-dimensional point clouds, end-to-end human activity recognition is achieved. During the model training process, a multithreshold fusion method is proposed for point cloud data to further enhance the model’s generalization and recognition capabilities. The proposed method is then validated using a public four-dimensional radar imaging dataset and compared with existing methods. The results show that the proposed method achieves a human activity recognition rate of 96.75% while consuming fewer parameters and computational resources, thereby verifying its effectiveness. |
| format | Article |
| id | doaj-art-178e06fc4bbb401ba94a652aa7f4a6f1 |
| institution | Kabale University |
| issn | 2095-283X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | China Science Publishing & Media Ltd. (CSPM) |
| record_format | Article |
| series | Leida xuebao |
| spelling | doaj-art-178e06fc4bbb401ba94a652aa7f4a6f12025-01-22T06:12:25ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2025-02-0114111510.12000/JR24110R24110A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point CloudsYongkun SONG0Tianxing YAN1Ke ZHANG2Xian LIU3Yongpeng DAI4Tian JIN5College of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, ChinaCollege of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, ChinaCollege of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, ChinaCollege of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaLow-frequency Ultra-WideBand (UWB) radar offers significant advantages in the field of human activity recognition owing to its excellent penetration and resolution. To address the issues of high computational complexity and extensive network parameters in existing action recognition algorithms, this study proposes an efficient and lightweight human activity recognition method using UWB radar based on spatiotemporal point clouds. First, four-dimensional motion data of the human body are collected using UWB radar. A discrete sampling method is then employed to convert the radar images into point cloud representations. Because human activity recognition is a classification problem on time series, this paper combines the PointNet++ network with the Transformer network to propose a lightweight spatiotemporal network. By extracting and analyzing the spatiotemporal features of four-dimensional point clouds, end-to-end human activity recognition is achieved. During the model training process, a multithreshold fusion method is proposed for point cloud data to further enhance the model’s generalization and recognition capabilities. The proposed method is then validated using a public four-dimensional radar imaging dataset and compared with existing methods. The results show that the proposed method achieves a human activity recognition rate of 96.75% while consuming fewer parameters and computational resources, thereby verifying its effectiveness.https://radars.ac.cn/cn/article/doi/10.12000/JR24110ultra-wideband (uwb) radaraction recognitionpoint cloudspointnet++transformer |
| spellingShingle | Yongkun SONG Tianxing YAN Ke ZHANG Xian LIU Yongpeng DAI Tian JIN A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds Leida xuebao ultra-wideband (uwb) radar action recognition point clouds pointnet++ transformer |
| title | A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds |
| title_full | A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds |
| title_fullStr | A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds |
| title_full_unstemmed | A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds |
| title_short | A Lightweight Human Activity Recognition Method for Ultra-wideband Radar Based on Spatiotemporal Features of Point Clouds |
| title_sort | lightweight human activity recognition method for ultra wideband radar based on spatiotemporal features of point clouds |
| topic | ultra-wideband (uwb) radar action recognition point clouds pointnet++ transformer |
| url | https://radars.ac.cn/cn/article/doi/10.12000/JR24110 |
| work_keys_str_mv | AT yongkunsong alightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT tianxingyan alightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT kezhang alightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT xianliu alightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT yongpengdai alightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT tianjin alightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT yongkunsong lightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT tianxingyan lightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT kezhang lightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT xianliu lightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT yongpengdai lightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds AT tianjin lightweighthumanactivityrecognitionmethodforultrawidebandradarbasedonspatiotemporalfeaturesofpointclouds |