A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences
Human action recognition has facilitated the development of artificial intelligence devices focusing on human activities and services. This technology has progressed by introducing 3D point clouds derived from depth cameras or radars. However, human behavior is intricate, and the involved point clou...
| Päätekijät: | , , , , |
|---|---|
| Aineistotyyppi: | Artikkeli |
| Kieli: | English |
| Julkaistu: |
MDPI AG
2024-07-01
|
| Sarja: | Applied Sciences |
| Aiheet: | |
| Linkit: | https://www.mdpi.com/2076-3417/14/14/6335 |
| _version_ | 1827179041472380928 |
|---|---|
| author | Chang Li Qian Huang Yingchi Mao Weiwen Qian Xing Li |
| author_facet | Chang Li Qian Huang Yingchi Mao Weiwen Qian Xing Li |
| author_sort | Chang Li |
| collection | DOAJ |
| description | Human action recognition has facilitated the development of artificial intelligence devices focusing on human activities and services. This technology has progressed by introducing 3D point clouds derived from depth cameras or radars. However, human behavior is intricate, and the involved point clouds are vast, disordered, and complicated, posing challenges to 3D action recognition. To solve these problems, we propose a Symmetric Fine-coarse Neural Network (SFCNet) that simultaneously analyzes human actions’ appearance and details. Firstly, the point cloud sequences are transformed and voxelized into structured 3D voxel sets. These sets are then augmented with an interval-frequency descriptor to generate 6D features capturing spatiotemporal dynamic information. By evaluating voxel space occupancy using thresholding, we can effectively identify the essential parts. After that, all the voxels with the 6D feature are directed to the global coarse stream, while the voxels within the key parts are routed to the local fine stream. These two streams extract global appearance features and critical body parts by utilizing symmetric PointNet++. Subsequently, attention feature fusion is employed to capture more discriminative motion patterns adaptively. Experiments conducted on public benchmark datasets NTU RGB+D 60 and NTU RGB+D 120 validate SFCNet’s effectiveness and superiority for 3D action recognition. |
| first_indexed | 2025-03-21T05:08:43Z |
| format | Article |
| id | doaj.art-9f45b12a524d446a9d35885a0f0b51a8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2025-03-21T05:08:43Z |
| publishDate | 2024-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9f45b12a524d446a9d35885a0f0b51a82024-07-26T12:32:56ZengMDPI AGApplied Sciences2076-34172024-07-011414633510.3390/app14146335A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud SequencesChang Li0Qian Huang1Yingchi Mao2Weiwen Qian3Xing Li4College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, ChinaCollege of Computer Science and Software Engineering, Hohai University, Nanjing 211100, ChinaCollege of Computer Science and Software Engineering, Hohai University, Nanjing 211100, ChinaCollege of Computer Science and Software Engineering, Hohai University, Nanjing 211100, ChinaCollege of Information Science and Technology and College of Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaHuman action recognition has facilitated the development of artificial intelligence devices focusing on human activities and services. This technology has progressed by introducing 3D point clouds derived from depth cameras or radars. However, human behavior is intricate, and the involved point clouds are vast, disordered, and complicated, posing challenges to 3D action recognition. To solve these problems, we propose a Symmetric Fine-coarse Neural Network (SFCNet) that simultaneously analyzes human actions’ appearance and details. Firstly, the point cloud sequences are transformed and voxelized into structured 3D voxel sets. These sets are then augmented with an interval-frequency descriptor to generate 6D features capturing spatiotemporal dynamic information. By evaluating voxel space occupancy using thresholding, we can effectively identify the essential parts. After that, all the voxels with the 6D feature are directed to the global coarse stream, while the voxels within the key parts are routed to the local fine stream. These two streams extract global appearance features and critical body parts by utilizing symmetric PointNet++. Subsequently, attention feature fusion is employed to capture more discriminative motion patterns adaptively. Experiments conducted on public benchmark datasets NTU RGB+D 60 and NTU RGB+D 120 validate SFCNet’s effectiveness and superiority for 3D action recognition.https://www.mdpi.com/2076-3417/14/14/6335point cloud analysis3D action recognitionpattern recognitiondeep learning |
| spellingShingle | Chang Li Qian Huang Yingchi Mao Weiwen Qian Xing Li A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences Applied Sciences point cloud analysis 3D action recognition pattern recognition deep learning |
| title | A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences |
| title_full | A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences |
| title_fullStr | A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences |
| title_full_unstemmed | A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences |
| title_short | A Novel Symmetric Fine-Coarse Neural Network for 3D Human Action Recognition Based on Point Cloud Sequences |
| title_sort | novel symmetric fine coarse neural network for 3d human action recognition based on point cloud sequences |
| topic | point cloud analysis 3D action recognition pattern recognition deep learning |
| url | https://www.mdpi.com/2076-3417/14/14/6335 |
| work_keys_str_mv | AT changli anovelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT qianhuang anovelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT yingchimao anovelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT weiwenqian anovelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT xingli anovelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT changli novelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT qianhuang novelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT yingchimao novelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT weiwenqian novelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences AT xingli novelsymmetricfinecoarseneuralnetworkfor3dhumanactionrecognitionbasedonpointcloudsequences |