Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation
In this study, we address the challenge of 3D human motion prediction from motion capture data, which has become critical in various applications such as autonomous vehicles and human-robot interaction. Previous deep learning-based methods have improved prediction accuracy, but require significant n...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10220091/ |
| _version_ | 1797680907534991360 |
|---|---|
| author | Hanwool Kim Choonsung Shin Yeong-Jun Cho |
| author_facet | Hanwool Kim Choonsung Shin Yeong-Jun Cho |
| author_sort | Hanwool Kim |
| collection | DOAJ |
| description | In this study, we address the challenge of 3D human motion prediction from motion capture data, which has become critical in various applications such as autonomous vehicles and human-robot interaction. Previous deep learning-based methods have improved prediction accuracy, but require significant network parameters and do not effectively consider independent joint movements. To overcome the limitations, we propose two lightweight network structures for human motion prediction: LG-Net and LGT-Net, which focus on the individual movements of distinct human limbs and their inter-dependencies. The LG-Net comprises local and global networks, while the LGT-Net combines the proposed LG-Net structure with Long and Short Term Memory (LSTM) cells to exploit temporal information. Our networks, designed to be extremely lightweight with only 0.08M and 0.5M parameters, achieve higher prediction performance compared to state-of-the-art methods. In addition, this study is the first to consider the root joint to improve motion prediction performance. The proposed approach demonstrates the potential for efficient and accurate human motion prediction in various applications. |
| first_indexed | 2024-03-11T23:37:04Z |
| format | Article |
| id | doaj.art-955c65e316314cc8985fcced6a23d804 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T23:37:04Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-955c65e316314cc8985fcced6a23d8042023-09-19T23:01:28ZengIEEEIEEE Access2169-35362023-01-0111988189882910.1109/ACCESS.2023.330563810220091Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global OrientationHanwool Kim0Choonsung Shin1Yeong-Jun Cho2https://orcid.org/0000-0002-0497-5660Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South KoreaGraduate School of Culture, Chonnam National University, Gwangju, South KoreaDepartment of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South KoreaIn this study, we address the challenge of 3D human motion prediction from motion capture data, which has become critical in various applications such as autonomous vehicles and human-robot interaction. Previous deep learning-based methods have improved prediction accuracy, but require significant network parameters and do not effectively consider independent joint movements. To overcome the limitations, we propose two lightweight network structures for human motion prediction: LG-Net and LGT-Net, which focus on the individual movements of distinct human limbs and their inter-dependencies. The LG-Net comprises local and global networks, while the LGT-Net combines the proposed LG-Net structure with Long and Short Term Memory (LSTM) cells to exploit temporal information. Our networks, designed to be extremely lightweight with only 0.08M and 0.5M parameters, achieve higher prediction performance compared to state-of-the-art methods. In addition, this study is the first to consider the root joint to improve motion prediction performance. The proposed approach demonstrates the potential for efficient and accurate human motion prediction in various applications.https://ieeexplore.ieee.org/document/10220091/Human motion predictionlightweight networkspatial and temporal information |
| spellingShingle | Hanwool Kim Choonsung Shin Yeong-Jun Cho Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation IEEE Access Human motion prediction lightweight network spatial and temporal information |
| title | Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation |
| title_full | Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation |
| title_fullStr | Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation |
| title_full_unstemmed | Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation |
| title_short | Human Motion Prediction by Combining Spatial and Temporal Information With Independent Global Orientation |
| title_sort | human motion prediction by combining spatial and temporal information with independent global orientation |
| topic | Human motion prediction lightweight network spatial and temporal information |
| url | https://ieeexplore.ieee.org/document/10220091/ |
| work_keys_str_mv | AT hanwoolkim humanmotionpredictionbycombiningspatialandtemporalinformationwithindependentglobalorientation AT choonsungshin humanmotionpredictionbycombiningspatialandtemporalinformationwithindependentglobalorientation AT yeongjuncho humanmotionpredictionbycombiningspatialandtemporalinformationwithindependentglobalorientation |