Name
Abstract | ||
|---|---|---|
In movement analysis frameworks, body pose may often be adequately represented in a simple, low-dimensional, and high-level space, while full body joints' locations constitute excessively redundant and complex information. We propose a method for estimating body pose in such high-level pose spaces, directly from a depth image and without relying on intermediate skeleton-based steps. Our method is based on a convolutional neural network (CNN) that maps the depth-silhouette of a person to its position in the pose space. We apply our method to a pose representation proposed in [16] that was initially built from skeleton data. We find our estimation of pose to be consistent with the original one, and to be suitable for use in the movement quality assessment framework of [16]. This opens the perspective of a wider applicability of the movement analysis method to movement types and view-angles that are not supported by its skeleton tracking algorithm. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/ICCVW.2015.49 | ICCV Workshops |
Keywords | Field | DocType |
skeleton-free body pose estimation,depth images,complex information,high-level pose spaces,convolutional neural network,CNN,person depth-silhouette,pose representation,movement quality assessment framework,movement analysis method,skeleton tracking algorithm | Computer vision,Pattern recognition,Visualization,Convolutional neural network,Computer science,3D pose estimation,Pose,Feature extraction,Artificial intelligence,Free body,Articulated body pose estimation,Hidden Markov model | Conference |
Volume | Issue | Citations |
2015 | 1 | 3 |
PageRank | References | Authors |
0.52 | 22 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ben Crabbe | 1 | 3 | 0.52 |
| Adeline Paiement | 2 | 61 | 7.88 |
| Sion L. Hannuna | 3 | 69 | 10.37 |
| Majid Mirmehdi | 4 | 955 | 96.94 |