Miha Peternel and Aleš Leonardis (2004) Visual Learning and Recognition of a Probabilistic Spatio-Temporal Model of Cyclic Human Locomotion. In: 17th International Conference on Pattern Recognition, 23-26 August 2004, Cambridge, UK. (In Press)
Abstract
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of continuous, phase aligned spatio-temporal curves from trajectories of random points tracked over several cycles of locomotion in a monocular video sequence. We analyze a PCA representation of a set of cyclic curves, pointing out properties of the representation which can be used for spatio-temporal alignment in tracking and recognition tasks. We model the curve distribution density by a mixture of Gaussians using expectation-maximization algorithm. For recognition, we use maximum a posteriori estimate combined with linear data adaptation. We tested the algorithms on CMU MoBo database with favourable results for the recognition of people “by walking” from monocular video sequences captured from the side view.
| Item Type: | Conference or Workshop Item (Paper) |
|---|
| Keywords: | computer vision, spatio-temporal modelling, probabilistic modelling, human locomotion, cyclic motion, spatio-temporal curves, principal component analysis, PCA, Gaussian mixture model, visual learning, visual recognition |
|---|
| Language of Content: | English |
|---|
| Related URLs: | |
|---|
| Institution: | University of Ljubljana |
|---|
| Department: | Faculty of Computer and Information Science |
|---|
| Divisions: | Faculty of Computer and Information Science > Computer Vision Laboratory |
|---|
| Item ID: | 127 |
|---|
| Date Deposited: | 09 Jul 2004 |
|---|
| Last Modified: | 11 Dec 2013 08:55 |
|---|
| URI: | http://eprints.fri.uni-lj.si/id/eprint/127 |
|---|
Actions (login required)
![[img]](http://eprints.fri.uni-lj.si/style/images/fileicons/application_pdf.png)
