Action Recognition by Joint Spatial-Temporal Motion Feature
This paper introduces a method for human action recognition based on optical flow motion features extraction. Automatic spatial and temporal alignments are combined together in order to encourage the temporal consistence on each action by an enhanced dynamic time warping (DTW) algorithm. At the same...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2013/605469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832556152206917632 |
|---|---|
| author | Weihua Zhang Yi Zhang Chaobang Gao Jiliu Zhou |
| author_facet | Weihua Zhang Yi Zhang Chaobang Gao Jiliu Zhou |
| author_sort | Weihua Zhang |
| collection | DOAJ |
| description | This paper introduces a method for human action recognition based on optical flow motion features extraction. Automatic spatial and temporal alignments are combined together in order to encourage the temporal consistence on each action by an enhanced dynamic time warping (DTW) algorithm. At the same time, a fast method based on coarse-to-fine DTW constraint to improve computational performance without reducing accuracy is induced. The main contributions of this study include (1) a joint spatial-temporal multiresolution optical flow computation method which can keep encoding more informative motion information than recent proposed methods, (2) an enhanced DTW method to improve temporal consistence of motion in action recognition, and (3) coarse-to-fine DTW constraint on motion features pyramids to speed up recognition performance. Using this method, high recognition accuracy is achieved on different action databases like Weizmann database and KTH database. |
| format | Article |
| id | doaj-art-a8a1b135dd644f94a4c46e244c28543b |
| institution | Kabale University |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-a8a1b135dd644f94a4c46e244c28543b2025-02-03T05:46:15ZengWileyJournal of Applied Mathematics1110-757X1687-00422013-01-01201310.1155/2013/605469605469Action Recognition by Joint Spatial-Temporal Motion FeatureWeihua Zhang0Yi Zhang1Chaobang Gao2Jiliu Zhou3School of Computer Science, Sichuan University, Chengdu 610065, ChinaSchool of Computer Science, Sichuan University, Chengdu 610065, ChinaCollege of Information Science and Technology, Chengdu University, Chengdu 610106, ChinaSchool of Computer Science, Sichuan University, Chengdu 610065, ChinaThis paper introduces a method for human action recognition based on optical flow motion features extraction. Automatic spatial and temporal alignments are combined together in order to encourage the temporal consistence on each action by an enhanced dynamic time warping (DTW) algorithm. At the same time, a fast method based on coarse-to-fine DTW constraint to improve computational performance without reducing accuracy is induced. The main contributions of this study include (1) a joint spatial-temporal multiresolution optical flow computation method which can keep encoding more informative motion information than recent proposed methods, (2) an enhanced DTW method to improve temporal consistence of motion in action recognition, and (3) coarse-to-fine DTW constraint on motion features pyramids to speed up recognition performance. Using this method, high recognition accuracy is achieved on different action databases like Weizmann database and KTH database.http://dx.doi.org/10.1155/2013/605469 |
| spellingShingle | Weihua Zhang Yi Zhang Chaobang Gao Jiliu Zhou Action Recognition by Joint Spatial-Temporal Motion Feature Journal of Applied Mathematics |
| title | Action Recognition by Joint Spatial-Temporal Motion Feature |
| title_full | Action Recognition by Joint Spatial-Temporal Motion Feature |
| title_fullStr | Action Recognition by Joint Spatial-Temporal Motion Feature |
| title_full_unstemmed | Action Recognition by Joint Spatial-Temporal Motion Feature |
| title_short | Action Recognition by Joint Spatial-Temporal Motion Feature |
| title_sort | action recognition by joint spatial temporal motion feature |
| url | http://dx.doi.org/10.1155/2013/605469 |
| work_keys_str_mv | AT weihuazhang actionrecognitionbyjointspatialtemporalmotionfeature AT yizhang actionrecognitionbyjointspatialtemporalmotionfeature AT chaobanggao actionrecognitionbyjointspatialtemporalmotionfeature AT jiliuzhou actionrecognitionbyjointspatialtemporalmotionfeature |