Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published June 20, 2005 | Published
Book Section - Chapter Open

Hybrid Models for Human Motion Recognition

Abstract

Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as a triangulated graph. Previous approaches learned models based just on positions and velocities of the body parts while ignoring their appearance. Moreover, a heuristic approach was commonly used to obtain translation invariance. In this paper we suggest an improved approach for learning such models and using them for human motion recognition. The suggested approach combines multiple cues, i.e., positions, velocities and appearance into both the learning and detection phases. Furthermore, we introduce global variables in the model, which can represent global properties such as translation, scale or view-point. The model is learned in an unsupervised manner from unlabelled data. We show that the suggested hybrid probabilistic model (which combines global variables, like translation, with local variables, like relative positions and appearances of body parts), leads to: (i) faster convergence of learning phase, (ii) robustness to occlusions, and, (iii) higher recognition rate.

Additional Information

© 2005 IEEE. Issue Date: 20-25 June 2005. Date of Current Version: 25 July 2005. We wish to thank Mark Paskin, Marzia Polito and Max Welling for proficuous discussions. This research was supported by the MURI award SA3318, by the Center of Neuromorphic Systems Engineering award EEC-9402726 and by JPL grant 1261654.

Attached Files

Published - FANcvpr05.pdf

Files

FANcvpr05.pdf
Files (383.9 kB)
Name Size Download all
md5:c27ea70efd9ca4c6a3a2b9a78addbc86
383.9 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
January 13, 2024