Spatial measures between human poses for classification and understanding

TY - GEN

T1 - Spatial measures between human poses for classification and understanding

AU - Hauberg, Søren

AU - Pedersen, Kim Steenstrup

N1 - Conference code: 7

PY - 2012

Y1 - 2012

N2 - Statistical analysis of humans, their motion and their behaviour is a very well-studied problem. With the availability of accurate motion capture systems, it has become possible to use such analysis for animation, understanding, compression and tracking of human motion. At the core of the analysis lies a measure for determining the distance between two human poses; practically always, this measure is the Euclidean distance between joint angle vectors. Recent work [7] has shown that articulated tracking systems can be vastly improved by replacing the Euclidean distance in joint angle space with the geodesic distance in the space of joint positions. However, due to the focus on tracking, no algorithms have, so far, been presented for measuring these distances between human poses. In this paper, we present an algorithm for computing geodesics in the Riemannian space of joint positions, as well as a fast approximation that allows for large-scale analysis. In the experiments we show that this measure significantly outperforms the traditional measure in classification, clustering and dimensionality reduction tasks.

AB - Statistical analysis of humans, their motion and their behaviour is a very well-studied problem. With the availability of accurate motion capture systems, it has become possible to use such analysis for animation, understanding, compression and tracking of human motion. At the core of the analysis lies a measure for determining the distance between two human poses; practically always, this measure is the Euclidean distance between joint angle vectors. Recent work [7] has shown that articulated tracking systems can be vastly improved by replacing the Euclidean distance in joint angle space with the geodesic distance in the space of joint positions. However, due to the focus on tracking, no algorithms have, so far, been presented for measuring these distances between human poses. In this paper, we present an algorithm for computing geodesics in the Riemannian space of joint positions, as well as a fast approximation that allows for large-scale analysis. In the experiments we show that this measure significantly outperforms the traditional measure in classification, clustering and dimensionality reduction tasks.

U2 - 10.1007/978-3-642-31567-1_3

DO - 10.1007/978-3-642-31567-1_3

M3 - Article in proceedings

SN - 978-3-642-31566-4

T3 - Lecture notes in computer science

SP - 26

EP - 36

BT - Articulated Motion and Deformable Objects

A2 - Perales, Francisco J.

A2 - Fisher, Robert B.

A2 - Moeslund, Thomas B.

PB - Springer

T2 - 7th International Conference on Articulated Motion and Deformable Objects

Y2 - 11 July 2012 through 13 July 2012

ER -