| Paper: | TA-P1.2 |
| Session: | Video Surveillance I / Document Image Processing & Analysis |
| Time: | Tuesday, September 18, 09:50 - 12:30 |
| Presentation: |
Poster
|
| Title: |
SEMI-SUPERVISED LEARNING OF SWITCHED DYNAMICAL MODELS FOR CLASSIFICATION OF HUMAN ACTIVITIES IN SURVEILLANCE APPLICATIONS |
| Authors: |
Jacinto Nascimento; Instituto de Sistemas e Robótica | | |
| | Mário Figueiredo; Instituto Superior Técnico | | |
| | Jorge Marques; Instituto Superior Técnico | | |
| Abstract: |
This work introduces a semi-supervised approach for learning generative models for classification/recognition of human trajectories, with application to surveillance. The classifier is based on switched dynamical models, with each model describing a specific motion regime. We present a semi-supervised modified version of the classical Baum-Welch algorithm, which is able to take into account a subset of known model labels. The experimental results reported, using both synthetic and real data, show that the classifier learned with semi-supervision leads to a higher classification accuracy than the fully unsupervised version, thus validating the proposed approach. |
