Surface and underwater human pose recognition based on temporal 3D point cloud deep learning
Abstract Airborne surface and underwater human pose recognition are crucial for various safety and surveillance applications, including the detection of individuals in distress or drowning situations. However, airborne optical cameras struggle to achieve simultaneous imaging of the surface and under...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-50658-4 |
| _version_ | 1827388606970331136 |
|---|---|
| author | Haijian Wang Zhenyu Wu Xuemei Zhao |
| author_facet | Haijian Wang Zhenyu Wu Xuemei Zhao |
| author_sort | Haijian Wang |
| collection | DOAJ |
| description | Abstract Airborne surface and underwater human pose recognition are crucial for various safety and surveillance applications, including the detection of individuals in distress or drowning situations. However, airborne optical cameras struggle to achieve simultaneous imaging of the surface and underwater because of limitations imposed by visible-light wavelengths. To address this problem, this study proposes the use of light detection and ranging (LiDAR) to simultaneously detect humans on the surface and underwater, whereby human poses are recognized using a neural network designed for irregular data. First, a temporal point-cloud dataset was constructed for surface and underwater human pose recognition to enhance the recognition of comparable movements. Subsequently, radius outlier removal (ROR) and statistical outlier removal (SOR) were employed to alleviate the impact of noise and outliers in the constructed dataset. Finally, different combinations of secondary sampling methods and sample sizes were tested to improve recognition accuracy using PointNet++. The experimental results show that the highest recognition accuracy reached 97.5012%, demonstrating the effectiveness of the proposed human pose detection and recognition method. |
| first_indexed | 2024-03-08T16:21:19Z |
| format | Article |
| id | doaj.art-48ddac4efed5422c8c603754b1bc23b2 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-08T16:21:19Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-48ddac4efed5422c8c603754b1bc23b22024-01-07T12:20:24ZengNature PortfolioScientific Reports2045-23222024-01-0114111510.1038/s41598-023-50658-4Surface and underwater human pose recognition based on temporal 3D point cloud deep learningHaijian Wang0Zhenyu Wu1Xuemei Zhao2School of Mechanical and Electrical Engineering, Guilin University of Electronic TechnologySchool of Mechanical and Electrical Engineering, Guilin University of Electronic TechnologySchool of Electronic Engineering and Automation, Guilin University of Electronic TechnologyAbstract Airborne surface and underwater human pose recognition are crucial for various safety and surveillance applications, including the detection of individuals in distress or drowning situations. However, airborne optical cameras struggle to achieve simultaneous imaging of the surface and underwater because of limitations imposed by visible-light wavelengths. To address this problem, this study proposes the use of light detection and ranging (LiDAR) to simultaneously detect humans on the surface and underwater, whereby human poses are recognized using a neural network designed for irregular data. First, a temporal point-cloud dataset was constructed for surface and underwater human pose recognition to enhance the recognition of comparable movements. Subsequently, radius outlier removal (ROR) and statistical outlier removal (SOR) were employed to alleviate the impact of noise and outliers in the constructed dataset. Finally, different combinations of secondary sampling methods and sample sizes were tested to improve recognition accuracy using PointNet++. The experimental results show that the highest recognition accuracy reached 97.5012%, demonstrating the effectiveness of the proposed human pose detection and recognition method.https://doi.org/10.1038/s41598-023-50658-4 |
| spellingShingle | Haijian Wang Zhenyu Wu Xuemei Zhao Surface and underwater human pose recognition based on temporal 3D point cloud deep learning Scientific Reports |
| title | Surface and underwater human pose recognition based on temporal 3D point cloud deep learning |
| title_full | Surface and underwater human pose recognition based on temporal 3D point cloud deep learning |
| title_fullStr | Surface and underwater human pose recognition based on temporal 3D point cloud deep learning |
| title_full_unstemmed | Surface and underwater human pose recognition based on temporal 3D point cloud deep learning |
| title_short | Surface and underwater human pose recognition based on temporal 3D point cloud deep learning |
| title_sort | surface and underwater human pose recognition based on temporal 3d point cloud deep learning |
| url | https://doi.org/10.1038/s41598-023-50658-4 |
| work_keys_str_mv | AT haijianwang surfaceandunderwaterhumanposerecognitionbasedontemporal3dpointclouddeeplearning AT zhenyuwu surfaceandunderwaterhumanposerecognitionbasedontemporal3dpointclouddeeplearning AT xuemeizhao surfaceandunderwaterhumanposerecognitionbasedontemporal3dpointclouddeeplearning |