THE QUEST FOR AUTOMATED LAND COVER CHANGE DETECTION USING SATELLITE TIME SERIES DATA

被引：0

作者：

Salmon, B. P. ^{[1
,2
]}

Olivier, J. C. ^{[1
,3
]}

Kleynhans, W. ^{[1
,2
]}

Wessels, K. J. ^{[2
]}

van den Bergh, F. ^{[2
]}

机构：

[1] Univ Pretoria, Dept Elect Elect & Comp Engn, ZA-0002 Pretoria, South Africa

[2] CSIR, Meraka Inst, Remote Sensing Res Unit, Pretoria, South Africa

[3] CSIR, Def Peace Safety & Secur Unit, Pretoria, South Africa

来源：

2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5 | 2009年

关键词：

Classification; feedforward neural networks; satellites; time series; CLASSIFICATION;

D O I：

10.1109/IGARSS.2009.5417328

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

This paper shows that a feedforward Multilayer Perceptron (MLP) operating over a temporal sliding window of multispectral time series MODerate-resolution Imaging Spectroradiometer (MODIS) satellite data is able to detect land cover change that was artificially Introduced by concatenating time series belonging to different types of land cover. The method employs an iteratively retrained MLP that is a supervised method, and thus captures all local environmental patterns. Depending on the length of the temporal sliding window used in the short-term Fourier transform, an overall change detection accuracy of between 87.62% and 97.02% was achieved. It is shown that for this type of simulated land cover change, where land cover change was abrupt, a short-term FFT window of 18 months or less, using only the two NDVI spectral bands of MODIS data was sufficient to detect change reliably.

引用

页码：2624 / +

页数：2

共 10 条

[1]

[Anonymous], 2005, NEURAL NETWORKS PATT

[2]

[Anonymous], 1999, Prentice-Hall Signal Processing Series

[3]

[Anonymous], 1994, Time Series Analysis, DOI DOI 10.1515/9780691218632

[4] Human modification of the landscape and surface climate in the next fifty years [J].