Learning a 3D Human Pose Distance Metric from Geometric Pose Descriptor.

Publication Type:
Journal Article
Citation:
IEEE Trans Vis Comput Graph, 2011, 17 (11), pp. 1676 - 1689
Issue Date:
2011-11
Full metadata record
Files in This Item:
Filename Description Size
pose.pdfPublished Version1.16 MB
Adobe PDF
Estimating 3D pose similarity is a fundamental problem on 3D motion data. Most previous work calculates L2-like distance of joint orientations or coordinates, which does not sufficiently reflect the pose similarity of human perception. In this paper, we present a new pose distance metric. First, we propose a new rich pose feature set called Geometric Pose Descriptor (GPD). GPD is more effective in encoding pose similarity by utilizing features on geometric relations among body parts, as well as temporal information such as velocities and accelerations. Based on GPD, we propose a semisupervised distance metric learning algorithm called Regularized Distance Metric Learning with Sparse Representation (RDSR), which integrates information from both unsupervised data relationship and labels. We apply the proposed pose distance metric to applications of motion transition decision and content-based pose retrieval. Quantitative evaluations demonstrate that our method achieves better results with only a small amount of human labels, showing that the proposed pose distance metric is a promising building block for various 3D-motion related applications.
Please use this identifier to cite or link to this item: