Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar
Through-wall human pose reconstruction and behavior recognition have enormous potential in fields like intelligent security and virtual reality. However, existing methods for through-wall human sensing often fail to adequately model four-Dimensional (4D) spatiotemporal features and overlook the infl...
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/JR24132 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591799458201600 |
|---|---|
| author | Rui ZHANG Hanqin GONG Ruiyuan SONG Yadong LI Zhi LU Dongheng ZHANG Yang HU Yan CHEN |
| author_facet | Rui ZHANG Hanqin GONG Ruiyuan SONG Yadong LI Zhi LU Dongheng ZHANG Yang HU Yan CHEN |
| author_sort | Rui ZHANG |
| collection | DOAJ |
| description | Through-wall human pose reconstruction and behavior recognition have enormous potential in fields like intelligent security and virtual reality. However, existing methods for through-wall human sensing often fail to adequately model four-Dimensional (4D) spatiotemporal features and overlook the influence of walls on signal quality. To address these issues, this study proposes an innovative architecture for through-wall human sensing using a 4D imaging radar. The core of this approach is the ST2W-AP fusion network, which is designed using a stepwise spatiotemporal separation strategy. This network overcomes the limitations of mainstream deep learning libraries that currently lack 4D convolution capabilities, which hinders the effective use of multiframe three-Dimensional (3D) voxel spatiotemporal domain information. By preserving 3D spatial information and using long-sequence temporal information, the proposed ST2W-AP network considerably enhances the pose estimation and behavior recognition performance. Additionally, to address the influence of walls on signal quality, this paper introduces a deep echo domain compensator that leverages the powerful fitting performance and parallel output characteristics of deep learning, thereby reducing the computational overhead of traditional wall compensation methods. Extensive experimental results demonstrate that compared with the best existing methods, the ST2W-AP network reduces the average joint position error by 33.57% and improves the F1 score for behavior recognition by 0.51%. |
| format | Article |
| id | doaj-art-d2d7eb5cd5334224b1d1eef3bd55c174 |
| 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-d2d7eb5cd5334224b1d1eef3bd55c1742025-01-22T06:12:25ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2025-02-01141446110.12000/JR24132R24132Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging RadarRui ZHANG0Hanqin GONG1Ruiyuan SONG2Yadong LI3Zhi LU4Dongheng ZHANG5Yang HU6Yan CHEN7School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaSchool of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaThrough-wall human pose reconstruction and behavior recognition have enormous potential in fields like intelligent security and virtual reality. However, existing methods for through-wall human sensing often fail to adequately model four-Dimensional (4D) spatiotemporal features and overlook the influence of walls on signal quality. To address these issues, this study proposes an innovative architecture for through-wall human sensing using a 4D imaging radar. The core of this approach is the ST2W-AP fusion network, which is designed using a stepwise spatiotemporal separation strategy. This network overcomes the limitations of mainstream deep learning libraries that currently lack 4D convolution capabilities, which hinders the effective use of multiframe three-Dimensional (3D) voxel spatiotemporal domain information. By preserving 3D spatial information and using long-sequence temporal information, the proposed ST2W-AP network considerably enhances the pose estimation and behavior recognition performance. Additionally, to address the influence of walls on signal quality, this paper introduces a deep echo domain compensator that leverages the powerful fitting performance and parallel output characteristics of deep learning, thereby reducing the computational overhead of traditional wall compensation methods. Extensive experimental results demonstrate that compared with the best existing methods, the ST2W-AP network reduces the average joint position error by 33.57% and improves the F1 score for behavior recognition by 0.51%.https://radars.ac.cn/cn/article/doi/10.12000/JR24132through-wallhuman pose estimationactivity recognitionrf sensingdeep learning |
| spellingShingle | Rui ZHANG Hanqin GONG Ruiyuan SONG Yadong LI Zhi LU Dongheng ZHANG Yang HU Yan CHEN Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar Leida xuebao through-wall human pose estimation activity recognition rf sensing deep learning |
| title | Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar |
| title_full | Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar |
| title_fullStr | Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar |
| title_full_unstemmed | Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar |
| title_short | Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar |
| title_sort | through wall human pose reconstruction and action recognition using four dimensional imaging radar |
| topic | through-wall human pose estimation activity recognition rf sensing deep learning |
| url | https://radars.ac.cn/cn/article/doi/10.12000/JR24132 |
| work_keys_str_mv | AT ruizhang throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT hanqingong throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT ruiyuansong throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT yadongli throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT zhilu throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT donghengzhang throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT yanghu throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar AT yanchen throughwallhumanposereconstructionandactionrecognitionusingfourdimensionalimagingradar |