eCite Digital Repository

A comparison of feature extraction methods within a spatio-temporal land cover change detection framework

Citation

Kleynhans, W and Salmon, BP and Olivier, JC and Wessels, KJ and van den Bergh, F, A comparison of feature extraction methods within a spatio-temporal land cover change detection framework, Proceedings of the IEEE Geoscience and Remote Sensing Symposium (IGARSS) 2011, 24-29 July 2011, Vancouver, Canada, pp. 688-691. ISBN 978-1-4577-1003-2 (2011) [Refereed Conference Paper]

DOI: doi:10.1109/IGARSS.2011.6049223

Abstract

In this paper, a change detection accuracy comparison is made between a recently proposed EKF method and a sliding window Fast Fourier Transform (FFT) alternative within a spatiotemporal change detection framework. Bothmethods produce a mean and amplitude parameter sequence which is then used to determine a change metric which yield a change of nochange decision after thresholding. The objective is to determine which of these methods produces a change metric value that is able to best discriminate between change and no-change.

Item Details

Item Type:Refereed Conference Paper
Keywords:time series, fast Fourier transforms, land cover change
Research Division:Engineering
Research Group:Electrical and Electronic Engineering
Research Field:Electrical and Electronic Engineering not elsewhere classified
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in Engineering
Author:Salmon, BP (Dr Brian Salmon)
Author:Olivier, JC (Professor JC Olivier)
ID Code:78841
Year Published:2011
Deposited By:Engineering
Deposited On:2012-07-30
Last Modified:2017-11-06
Downloads:0

Repository Staff Only: item control page