Name
Abstract | ||
|---|---|---|
Depth-images-based human pose estimation is facing two challenges: how to extract features which are discriminative to variations in human poses and robust against noise, and how to reliably learn body joints based on their dependence structure. To tackle the first problem, we propose a novel 3D Local Shape Context feature extracted from human body silhouette to characterise the local structure of body joints. To tackle the second problem, we incorporate a graphical model into regression forests to exploit structural constrains. Experiments demonstrate that our method can efficiently learn local body structures and localise joints. Compared with the state-of-the-art methods, our method significantly improves the accuracy of pose estimation from depth images. (C) 2015 Published by Elsevier B.V. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.neucom.2015.02.068 | Neurocomputing |
Keywords | Field | DocType |
3D local shape context,Graphical models,Pose estimation,Regression forests | Silhouette,Pose,Artificial intelligence,Articulated body pose estimation,Shape context,Discriminative model,Computer vision,Pattern recognition,3D pose estimation,Graphical model,Machine learning,Mathematics,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
164 | C | 0925-2312 |
Citations | PageRank | References |
8 | 0.50 | 27 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Li He | 1 | 43 | 2.16 |
| Guijin Wang | 2 | 405 | 49.34 |
| QM | 3 | 464 | 72.05 |
| Jing-Hao Xue | 4 | 393 | 46.48 |