Name
Abstract | ||
|---|---|---|
Depth image based human action recognition has attracted many attentions due to the popularity of the depth sensors. However, accurate recognition still remains a challenge because of various object appearances, poses and video sequences. In this paper, a novel skeleton joints descriptor based on 3D Moving Trend and Geometry (3DMTG) property is proposed for human action recognition. Specifically, a histogram of 3D moving directions between consecutive frames for each joint is constructed to represent the 3D moving trend feature in spatial domain. The geometry information of joints in each frame is modelled by the relative motion with the initial status. The proposed feature descriptor is evaluated on two popular datasets. The experimental results demonstrate the superior performance of our method over the state-of-the-art methods, especially the higher recognition rates for complex actions. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/SMC.2016.7844262 | 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC) |
Keywords | Field | DocType |
Human action recognition,3D Moving Trend,geometry property | Histogram,Computer vision,Feature descriptor,Computer science,Relative motion,Action recognition,Image based,Feature extraction,Artificial intelligence,Geometry,Trajectory | Conference |
ISSN | ISBN | Citations |
1062-922X | 978-1-5090-1898-7 | 0 |
PageRank | References | Authors |
0.34 | 21 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bangli Liu | 1 | 11 | 2.85 |
| Hui Yu | 2 | 128 | 21.50 |
| Xiaolong Zhou | 3 | 0 | 0.34 |
| Dan Tang | 4 | 0 | 0.34 |
| Honghai Liu | 5 | 1974 | 178.69 |