Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar
Abstract Compared with traditional approaches that used vision sensors which can provide a high‐resolution representation of targets, millimetre‐wave radar is robust to scene lighting and weather conditions, and has more applications. Current methods of human skeletal pose estimation can reconstruct...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-IET
2022-07-01
|
| Series: | IET Biometrics |
| Online Access: | https://doi.org/10.1049/bme2.12081 |
| _version_ | 1797422402932572160 |
|---|---|
| author | Jinxiao Zhong Liangnian Jin Ran Wang |
| author_facet | Jinxiao Zhong Liangnian Jin Ran Wang |
| author_sort | Jinxiao Zhong |
| collection | DOAJ |
| description | Abstract Compared with traditional approaches that used vision sensors which can provide a high‐resolution representation of targets, millimetre‐wave radar is robust to scene lighting and weather conditions, and has more applications. Current methods of human skeletal pose estimation can reconstruct targets, but they lose the spatial information or don't take the density of point cloud into consideration. We propose a skeletal pose estimation method that combines point convolution to extract features from the point cloud. By extracting the local information and density of each point in the point cloud of the target, the spatial location and structure information of the target can be obtained, and the accuracy of the pose estimation is increased. The extraction of point cloud features is based on point‐by‐point convolution, that is, different weights are applied to different features of each point, which also increases the nonlinear expression ability of the model. Experiments show that the proposed approach is effective. We offer more distinct skeletal joints and a lower mean absolute error, average localisation errors of 6.1 cm in X, 3.5 cm in Y and 3.3 cm in Z, respectively. |
| first_indexed | 2024-03-09T07:31:48Z |
| format | Article |
| id | doaj.art-f398ccf98cef41d595cdfb3c0529a2f2 |
| institution | Directory Open Access Journal |
| issn | 2047-4938 2047-4946 |
| language | English |
| last_indexed | 2024-03-09T07:31:48Z |
| publishDate | 2022-07-01 |
| publisher | Hindawi-IET |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj.art-f398ccf98cef41d595cdfb3c0529a2f22023-12-03T06:09:58ZengHindawi-IETIET Biometrics2047-49382047-49462022-07-0111433334210.1049/bme2.12081Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radarJinxiao Zhong0Liangnian Jin1Ran Wang2Institute of Information and Communication Guilin University of Electronic Technology Guilin ChinaInstitute of Information and Communication Guilin University of Electronic Technology Guilin ChinaInstitute of Information and Communication Guilin University of Electronic Technology Guilin ChinaAbstract Compared with traditional approaches that used vision sensors which can provide a high‐resolution representation of targets, millimetre‐wave radar is robust to scene lighting and weather conditions, and has more applications. Current methods of human skeletal pose estimation can reconstruct targets, but they lose the spatial information or don't take the density of point cloud into consideration. We propose a skeletal pose estimation method that combines point convolution to extract features from the point cloud. By extracting the local information and density of each point in the point cloud of the target, the spatial location and structure information of the target can be obtained, and the accuracy of the pose estimation is increased. The extraction of point cloud features is based on point‐by‐point convolution, that is, different weights are applied to different features of each point, which also increases the nonlinear expression ability of the model. Experiments show that the proposed approach is effective. We offer more distinct skeletal joints and a lower mean absolute error, average localisation errors of 6.1 cm in X, 3.5 cm in Y and 3.3 cm in Z, respectively.https://doi.org/10.1049/bme2.12081 |
| spellingShingle | Jinxiao Zhong Liangnian Jin Ran Wang Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar IET Biometrics |
| title | Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar |
| title_full | Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar |
| title_fullStr | Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar |
| title_full_unstemmed | Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar |
| title_short | Point‐convolution‐based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple‐input multiple‐output radar |
| title_sort | point convolution based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple input multiple output radar |
| url | https://doi.org/10.1049/bme2.12081 |
| work_keys_str_mv | AT jinxiaozhong pointconvolutionbasedhumanskeletalposeestimationonmillimetrewavefrequencymodulatedcontinuouswavemultipleinputmultipleoutputradar AT liangnianjin pointconvolutionbasedhumanskeletalposeestimationonmillimetrewavefrequencymodulatedcontinuouswavemultipleinputmultipleoutputradar AT ranwang pointconvolutionbasedhumanskeletalposeestimationonmillimetrewavefrequencymodulatedcontinuouswavemultipleinputmultipleoutputradar |