Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition
This paper presents a new framework for human action recognition by fusing human motion with skeletal joints. First, adaptive hierarchical depth motion maps (AH-DMMs) are proposed to capture the shape and motion cues of action sequences. Specifically, AH-DMMs are calculated over adaptive hierarchica...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/100166 http://hdl.handle.net/10220/48566 |
| _version_ | 1811690830063206400 |
|---|---|
| author | Ding, Runwei He, Qinqin Liu, Hong Liu, Mengyuan |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Ding, Runwei He, Qinqin Liu, Hong Liu, Mengyuan |
| author_sort | Ding, Runwei |
| collection | NTU |
| description | This paper presents a new framework for human action recognition by fusing human motion with skeletal joints. First, adaptive hierarchical depth motion maps (AH-DMMs) are proposed to capture the shape and motion cues of action sequences. Specifically, AH-DMMs are calculated over adaptive hierarchical windows and Gabor filters are used to encode the texture information of AH-DMMs. Then, spatial distances of skeletal joint positions are computed to characterize the structure information of the human body. Finally, two types of fusion methods including feature-level fusion and decision-level fusion are employed to combine the motion cues and structure information. The experimental results on public benchmark datasets, i.e., MSRAction3D and UTKinect-Action, show the effectiveness of the proposed method. |
| first_indexed | 2024-10-01T06:10:13Z |
| format | Journal Article |
| id | ntu-10356/100166 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:10:13Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/1001662020-03-07T14:02:39Z Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition Ding, Runwei He, Qinqin Liu, Hong Liu, Mengyuan School of Electrical and Electronic Engineering Action Recognition Depth Data DRNTU::Engineering::Electrical and electronic engineering This paper presents a new framework for human action recognition by fusing human motion with skeletal joints. First, adaptive hierarchical depth motion maps (AH-DMMs) are proposed to capture the shape and motion cues of action sequences. Specifically, AH-DMMs are calculated over adaptive hierarchical windows and Gabor filters are used to encode the texture information of AH-DMMs. Then, spatial distances of skeletal joint positions are computed to characterize the structure information of the human body. Finally, two types of fusion methods including feature-level fusion and decision-level fusion are employed to combine the motion cues and structure information. The experimental results on public benchmark datasets, i.e., MSRAction3D and UTKinect-Action, show the effectiveness of the proposed method. Published version 2019-06-06T06:49:53Z 2019-12-06T20:17:42Z 2019-06-06T06:49:53Z 2019-12-06T20:17:42Z 2018 Journal Article Ding, R., He, Q., Liu, H., & Liu, M. (2019). Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition. IEEE Access, 7, 5597-5608. doi:10.1109/ACCESS.2018.2886362 https://hdl.handle.net/10356/100166 http://hdl.handle.net/10220/48566 10.1109/ACCESS.2018.2886362 en IEEE Access © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information 12 p. application/pdf |
| spellingShingle | Action Recognition Depth Data DRNTU::Engineering::Electrical and electronic engineering Ding, Runwei He, Qinqin Liu, Hong Liu, Mengyuan Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| title | Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| title_full | Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| title_fullStr | Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| title_full_unstemmed | Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| title_short | Combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| title_sort | combining adaptive hierarchical depth motion maps with skeletal joints for human action recognition |
| topic | Action Recognition Depth Data DRNTU::Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/100166 http://hdl.handle.net/10220/48566 |
| work_keys_str_mv | AT dingrunwei combiningadaptivehierarchicaldepthmotionmapswithskeletaljointsforhumanactionrecognition AT heqinqin combiningadaptivehierarchicaldepthmotionmapswithskeletaljointsforhumanactionrecognition AT liuhong combiningadaptivehierarchicaldepthmotionmapswithskeletaljointsforhumanactionrecognition AT liumengyuan combiningadaptivehierarchicaldepthmotionmapswithskeletaljointsforhumanactionrecognition |