Home -> Projects ->Event Detection in Videos

Member Login

Jump to: Publications | Releases

Description

This project explores the use of volumetric features for event detection. We propose a novel method to correlate spatio-temporal shapes to video clips that have been automatically segmented. Our method works on over-segmented videos, which means that we do not require background subtraction for reliable object segmentation. Our method, when combined with a recent flow-based correlation technique, can detect a wide range of actions in video. For more information, see this project's homepage.

Publications

Releases [ Members Only ]