Publication Type:

Journal Article

Authors:

Nair, P.P.

Source:

International Journal of Remote Sensing, Volume 32, Number 17, p.4933-4941 (2011)

URL:

http://www.scopus.com/inward/record.url?eid=2-s2.0-80053123333&partnerID=40&md5=e4b39ff0b4ed1233edf7cce2f1b45829

Keywords:

algorithm, Algorithms, Dynamic weight, Expert networks, image classification, Image data, land classification, land cover, Land cover classification, Maximum likelihood, maximum likelihood analysis, Mixture of experts, Multi gradient, Multi sensor images, Multi-class classification, Network architecture, Supervised classification, Synaptic weight, Synthetic aperture radar, Synthetic aperture radar images, Training algorithms

Abstract:

An algorithm for supervised classification of multisensor images is proposed. The mixture of experts (ME) architecture with dynamic weight allocation is used for multiclass classification. Here the classification is treated as a maximum likelihood problem and the synaptic weights of the expert network and gating network are updated by a stochastic multigradient approach. Data from an optical sensor with four bands and a synthetic aperture radar (SAR) image of the same scene has been fused and classified. The algorithm is compared to some other advanced training algorithms in the literature for the same image data. © 2011 Taylor & Francis.

Notes:

cited By (since 1996)0

Cite this Research Publication

P. P. Nair, “A multigradient algorithm using a mixture of experts architecture for land cover classification of multisensor images”, International Journal of Remote Sensing, vol. 32, pp. 4933-4941, 2011.