Fanti, Claudio and Zelnik-Manor, Lihi and Perona, Pietro
(2005)
Hybrid Models for Human Motion Recognition.
In:
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
Proceedings - IEEE Computer Society Conference on Ccmputer Vision and Pattern Recognition.
IEEE
, Los Alamitos, CA, pp. 1166-1173.
ISBN 0-7695-2372-2.
https://resolver.caltech.edu/CaltechAUTHORS:20110714-150011256
![[img]](https://authors.library.caltech.edu/style/images/fileicons/application_pdf.png)  Preview |
|
PDF
- Published Version
See Usage Policy.
383kB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20110714-150011256
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.
Item Type: | Book Section |
---|
Related URLs: | |
---|
ORCID: | |
---|
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. |
---|
Funders: | Funding Agency | Grant Number |
---|
Multidisciplinary University Research Initiative (MURI) | SA3318 | Center for Neuromorphic Systems Engineering, Caltech | UNSPECIFIED | JPL | 1261654 | NSF | EEC-9402726 |
|
---|
Other Numbering System: | Other Numbering System Name | Other Numbering System ID |
---|
INSPEC Accession Number | 8599300 |
|
---|
Series Name: | Proceedings - IEEE Computer Society Conference on Ccmputer Vision and Pattern Recognition |
---|
DOI: | 10.1109/CVPR.2005.179 |
---|
Record Number: | CaltechAUTHORS:20110714-150011256 |
---|
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20110714-150011256 |
---|
Official Citation: | Fanti, C.; Zelnik-Manor, L.; Perona, P.; , "Hybrid models for human motion recognition," Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on , vol.1, no., pp. 1166- 1173 vol. 1, 20-25 June 2005
doi: 10.1109/CVPR.2005.179
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1467398&isnumber=31472
|
---|
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. |
---|
ID Code: | 24429 |
---|
Collection: | CaltechAUTHORS |
---|
Deposited By: |
Tony Diaz
|
---|
Deposited On: | 15 Jul 2011 22:02 |
---|
Last Modified: | 09 Nov 2021 16:23 |
---|
Repository Staff Only: item control page