Abstract | ||
---|---|---|
In this paper, we propose how to recognize upper-body poses using depth image based cylindrical coordinate system. In order to recognize the pose, we configure the cylindrical coordinate system belong to body features and the distance which is configured from camera to center of body using the pose candidate images. And we extract vectors of the features using depth information which are presented brightness values. The extracted vectors are mapped to radial feature space and classified pose pattern. And the pose patterns are learned using average of the feature points and recognized the poses by comparing pre-defined pose patterns using Euclidean distance. In this paper, in order to classify the features of the upper poses, we proposed method which can be composed of the poses and the upper pose patterns. The poses and the pose patterns are composed by using distance and angle from the center of the cylindrical coordinate system. In this paper, we purpose to extract effective pose information using simple operation applying dynamic cylindrical model to pose candidate images. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/FCV.2013.6485475 | Korea-Japan Joint Workshop on Frontiers of Computer Vision |
Keywords | Field | DocType |
pose recognition,cylindrical coordinate system | Computer vision,Feature vector,Cylindrical coordinate system,Pattern recognition,Euclidean distance,3D pose estimation,Feature extraction,Pose,Artificial intelligence,Contextual image classification,Mathematics,Brightness | Conference |
ISSN | Citations | PageRank |
2165-1051 | 0 | 0.34 |
References | Authors | |
4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jae-wan Park | 1 | 0 | 1.69 |
Dae-Hyeon Song | 2 | 0 | 0.68 |
Chil-woo Lee | 3 | 130 | 49.30 |