Capturing the relative distribution of features for action recognition
Oshin, O, Gilbert, A and Bowden, R (2011) Capturing the relative distribution of features for action recognition In: 2011 IEEE FG, 2011-03-21 - 2011-03-25, Santa Barbara, USA.
Available under License : See the attached licence file.
This paper presents an approach to the categorisation of spatio-temporal activity in video, which is based solely on the relative distribution of feature points. Introducing a Relative Motion Descriptor for actions in video, we show that the spatio-temporal distribution of features alone (without explicit appearance information) effectively describes actions, and demonstrate performance consistent with state-of-the-art. Furthermore, we propose that for actions where noisy examples exist, it is not optimal to group all action examples as a single class. Therefore, rather than engineering features that attempt to generalise over noisy examples, our method follows a different approach: We make use of Random Sampling Consensus (RANSAC) to automatically discover and reject outlier examples within classes. We evaluate the Relative Motion Descriptor and outlier rejection approaches on four action datasets, and show that outlier rejection using RANSAC provides a consistent and notable increase in performance, and demonstrate superior performance to more complex multiple-feature based approaches.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||Copyright 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.|
|Divisions:||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Depositing User:||Symplectic Elements|
|Date Deposited:||31 May 2012 08:56|
|Last Modified:||23 Sep 2013 19:24|
Actions (login required)
Downloads per month over past year