Feature detector and descriptor evaluation in human action recognition

Shao, Ling and Mattivi, Riccardo (2010) Feature detector and descriptor evaluation in human action recognition. In: CIVR 2010 - ACM International Conference on Image and Video Retrieval, 5th - 7th July 2010, Xi'an, China.

Full text not available from this repository. (Request a copy)

Abstract

In this paper, we evaluate and compare different feature detection and feature description methods for part-based approaches in human action recognition. Different methods have been proposed in the literature for both feature detection of space-time interest points and description of local video patches. It is however unclear which method performs better in the field of human action recognition. We compare, in the feature detection section, Dollar's method, Laptev's method, a bank of 3D-Gabor filters and a method based on Space-Time Differences of Gaussians. We also compare and evaluate different descriptors such as Gradient, HOG-HOF, 3D SIFT and an enhanced version of LBP-TOP. We show the combination of Dollar's detection method and the improved LBP-TOP descriptor to be computationally efficient and to reach the best recognition accuracy on the KTH database.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Human Action Recognition, LBP-TOP, Bag of Words, Feature Detectors, Feature Descriptors
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	17 Jun 2015 10:32
Last Modified:	12 Oct 2019 22:51
URI:	http://nrl.northumbria.ac.uk/id/eprint/22983

Downloads