Learning to recognise spatio-temporal interest points

Oshin, OT, Gilbert, A, Illingworth, J and Bowden, R (2009) Learning to recognise spatio-temporal interest points pp. 14-30.

Full text not available from this repository.

Abstract

In this chapter, we present a generic classifier for detecting spatio-temporal interest points within video, the premise being that, given an interest point detector, we can learn a classifier that duplicates its functionality and which is both accurate and computationally efficient. This means that interest point detection can be achieved independent of the complexity of the original interest point formulation. We extend the naive Bayesian classifier of Randomised Ferns to the spatio-temporal domain and learn classifiers that duplicate the functionality of common spatio-temporal interest point detectors. Results demonstrate accurate reproduction of results with a classifier that can be applied exhaustively to video at frame-rate, without optimisation, in a scanning window approach. © 2010, IGI Global.

Item Type:	Article
Divisions :	Surrey research (other units)
Authors :	Name Email ORCID Oshin, OT Gilbert, A a.gilbert@surrey.ac.uk Illingworth, J j.illingworth@surrey.ac.uk Bowden, R r.bowden@surrey.ac.uk
Date :	1 December 2009
DOI :	10.4018/978-1-60566-900-7.ch002
Depositing User :	Symplectic Elements
Date Deposited :	17 May 2017 13:15
Last Modified :	24 Jan 2020 23:40
URI:	http://epubs.surrey.ac.uk/id/eprint/838504

Actions (login required)

View Item

Downloads