You are here

FEATURE PRUNING FOR ACTION RECOGNITION IN COMPLEX ENVIRONMENT

Download pdf | Full Screen View

Date Issued:
2011
Abstract/Description:
A significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We introduce a new action database, created from the Weizmann database, that reveals a significant weakness in systems based on popular cuboid descriptors. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the descriptor level and must be addressed by modifying descriptors.
Title: FEATURE PRUNING FOR ACTION RECOGNITION IN COMPLEX ENVIRONMENT.
15 views
7 downloads
Name(s): Nagaraja, Adarsh, Author
Tappen, Marshall, Committee Chair
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2011
Publisher: University of Central Florida
Language(s): English
Abstract/Description: A significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We introduce a new action database, created from the Weizmann database, that reveals a significant weakness in systems based on popular cuboid descriptors. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the descriptor level and must be addressed by modifying descriptors.
Identifier: CFE0003882 (IID), ucf:48721 (fedora)
Note(s): 2011-08-01
M.S.
Engineering and Computer Science, School of Electrical Engineering and Computer Science
Masters
This record was generated from author submitted information.
Subject(s): Action recognition
bag of words
support vector machines
K-means clustering
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0003882
Restrictions on Access: public
Host Institution: UCF

In Collections