Mining Key Skeleton Poses with Latent SVM for Action Recognition
Human action recognition based on 3D skeleton has become an active research field in recent years with the recently developed commodity depth sensors. Most published methods analyze an entire 3D depth data, construct mid-level part representations, or use trajectory descriptor of spatial-temporal in...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Applied Computational Intelligence and Soft Computing |
| Online Access: | http://dx.doi.org/10.1155/2017/5861435 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563873699332096 |
|---|---|
| author | Xiaoqiang Li Yi Zhang Dong Liao |
| author_facet | Xiaoqiang Li Yi Zhang Dong Liao |
| author_sort | Xiaoqiang Li |
| collection | DOAJ |
| description | Human action recognition based on 3D skeleton has become an active research field in recent years with the recently developed commodity depth sensors. Most published methods analyze an entire 3D depth data, construct mid-level part representations, or use trajectory descriptor of spatial-temporal interest point for recognizing human activities. Unlike previous work, a novel and simple action representation is proposed in this paper which models the action as a sequence of inconsecutive and discriminative skeleton poses, named as key skeleton poses. The pairwise relative positions of skeleton joints are used as feature of the skeleton poses which are mined with the aid of the latent support vector machine (latent SVM). The advantage of our method is resisting against intraclass variation such as noise and large nonlinear temporal deformation of human action. We evaluate the proposed approach on three benchmark action datasets captured by Kinect devices: MSR Action 3D dataset, UTKinect Action dataset, and Florence 3D Action dataset. The detailed experimental results demonstrate that the proposed approach achieves superior performance to the state-of-the-art skeleton-based action recognition methods. |
| format | Article |
| id | doaj-art-df12002a3ad7447b88b978a2a6ab92cb |
| institution | Kabale University |
| issn | 1687-9724 1687-9732 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Computational Intelligence and Soft Computing |
| spelling | doaj-art-df12002a3ad7447b88b978a2a6ab92cb2025-02-03T01:12:20ZengWileyApplied Computational Intelligence and Soft Computing1687-97241687-97322017-01-01201710.1155/2017/58614355861435Mining Key Skeleton Poses with Latent SVM for Action RecognitionXiaoqiang Li0Yi Zhang1Dong Liao2School of Computer Engineering and Science, Shanghai University, Shanghai, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai, ChinaSchool of Mathematic and Statistics, Nanyang Normal University, Nanyang, ChinaHuman action recognition based on 3D skeleton has become an active research field in recent years with the recently developed commodity depth sensors. Most published methods analyze an entire 3D depth data, construct mid-level part representations, or use trajectory descriptor of spatial-temporal interest point for recognizing human activities. Unlike previous work, a novel and simple action representation is proposed in this paper which models the action as a sequence of inconsecutive and discriminative skeleton poses, named as key skeleton poses. The pairwise relative positions of skeleton joints are used as feature of the skeleton poses which are mined with the aid of the latent support vector machine (latent SVM). The advantage of our method is resisting against intraclass variation such as noise and large nonlinear temporal deformation of human action. We evaluate the proposed approach on three benchmark action datasets captured by Kinect devices: MSR Action 3D dataset, UTKinect Action dataset, and Florence 3D Action dataset. The detailed experimental results demonstrate that the proposed approach achieves superior performance to the state-of-the-art skeleton-based action recognition methods.http://dx.doi.org/10.1155/2017/5861435 |
| spellingShingle | Xiaoqiang Li Yi Zhang Dong Liao Mining Key Skeleton Poses with Latent SVM for Action Recognition Applied Computational Intelligence and Soft Computing |
| title | Mining Key Skeleton Poses with Latent SVM for Action Recognition |
| title_full | Mining Key Skeleton Poses with Latent SVM for Action Recognition |
| title_fullStr | Mining Key Skeleton Poses with Latent SVM for Action Recognition |
| title_full_unstemmed | Mining Key Skeleton Poses with Latent SVM for Action Recognition |
| title_short | Mining Key Skeleton Poses with Latent SVM for Action Recognition |
| title_sort | mining key skeleton poses with latent svm for action recognition |
| url | http://dx.doi.org/10.1155/2017/5861435 |
| work_keys_str_mv | AT xiaoqiangli miningkeyskeletonposeswithlatentsvmforactionrecognition AT yizhang miningkeyskeletonposeswithlatentsvmforactionrecognition AT dongliao miningkeyskeletonposeswithlatentsvmforactionrecognition |