The use of a multilayer perceptron for detecting new human settlements from a time series of MODIS images

dc.contributor.authorSalmon, Brian Paxton
dc.contributor.authorOlivier, Jan Corne
dc.contributor.authorKleynhans, Waldo
dc.contributor.authorWessels, K.J. (Konrad)
dc.contributor.authorVan den Bergh, Frans
dc.contributor.authorSteenkamp, Karen C.
dc.date.accessioned2012-08-24T14:27:26Z
dc.date.available2012-08-24T14:27:26Z
dc.date.issued2011-12
dc.description.abstractThis paper presents a novel land cover change detection method that employs a sliding window over hyper-temporal multi-spectral images acquired from the 7 bands of the MODerate-resolution Imaging Spectroradiometer (MODIS) land surface reflectance product. The method uses a Feedforward Multilayer Perceptron (MLP) for supervised change detection that operates on multi-spectral time series extracted with a sliding window from the dataset. The method was evaluated on both real and simulated land cover change examples. The simulated land cover change comprises of concatenated time series that are produced by blending actual time series of pixels from human settlements to those from adjacent areas covered by natural vegetation. The method employs an iteratively retrained MLP to capture all local patterns and to compensate for the time-varying climate in the geographical area. The iteratively retrained MLP was compared to a classical batch mode trained MLP. Depending on the length of the temporal sliding window used, an overall change detection accuracy between 83% and 90% was achieved. It is shown that a sliding window of 6 months using all 7 bands of MODIS data is sufficient to detect land cover change reliably. Window sizes of 18 months and longer provide minor improvements to classification accuracy and change detection performance at the cost of longer time delays.en_US
dc.description.librarianai2012en
dc.description.sponsorshipThe CSIR Strategic Research Panelen_US
dc.description.urihttp://www.elsevier.com/locate/jagen_US
dc.identifier.citationB.P. Salmon, J.C. Olivier, W. Kleynhans, K.J. Wessles, F. van den Bergh & K.C. Steenkamp, Use of a multilayer perceptron for detecting new human settlements from a time series of MODIS images, International Journal of Applied Earth Observation and Geoinformation, vol. 13, no. 6, pp. 873-883, (2011), doi: 10.1016/j.jag.2011.06.007.en_US
dc.identifier.issn0303-2434 (print)
dc.identifier.issn1872-826X (online)
dc.identifier.other10.1016/j.jag.2011.06.007
dc.identifier.urihttp://hdl.handle.net/2263/19643
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.rights© 2011 Elsevier B.V. All rights reserved.en_US
dc.subjectChange detectionen_US
dc.subjectFeedforward neural networksen_US
dc.subjectSatelliteen_US
dc.subjectTime seriesen_US
dc.subject.lcshLand coveren
dc.subject.lcshTime-series analysisen
dc.subject.lcshHuman settlementsen
dc.subject.lcshLand settlementen
dc.subject.lcshRemote-sensing imagesen
dc.subject.lcshPerceptronsen
dc.subject.lcshFeedforward control systemsen
dc.subject.lcshMODIS (Spectroradiometer)en
dc.titleThe use of a multilayer perceptron for detecting new human settlements from a time series of MODIS imagesen_US
dc.typePostprint Articleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Salmon_Use(2011).pdf
Size:
825.52 KB
Format:
Adobe Portable Document Format
Description:
Postprint Article

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: