The use of the Hopfield neural network to measure sea-surface velocities from satellite images
The use of the Hopfield neural network to measure sea-surface velocities from satellite images
The knowledge of ocean surface circulation is of major
importance for many applications, including the understanding
of global climate, resources exploitation, and containment of
chemical spills. In this letter, sea-surface feature tracking based
on the Hopfield neural network (NN) is described. The method is
based on the minimization of an energy function that represents
the feature tracking problem. A Hopfield NN is used to merge
cross-correlation information with prior knowledge of sea-surface
flows and image contextual information. It has been tested on
real satellite images. A set of five Advanced Very High Resolution
Radiometer thermal images of the coastal zone of California, along with a data set of coincident surface drifters positions, was used to test the method. Results of the new analysis are compared within situ data and previous results using other techniques. The method can be used on various kinds of images for tracking and also find other applications in image registration and pattern recognition.
feature extraction, hopfield networks, neural networks (NNs), sea surface, tracking.
624-628
Cote, S.
ffd99deb-a9e2-4469-9335-fce9b3f477a9
Tatnall, A.R.L.
2c9224b6-4faa-4bfd-9026-84e37fa6bdf3
October 2007
Cote, S.
ffd99deb-a9e2-4469-9335-fce9b3f477a9
Tatnall, A.R.L.
2c9224b6-4faa-4bfd-9026-84e37fa6bdf3
Cote, S. and Tatnall, A.R.L.
(2007)
The use of the Hopfield neural network to measure sea-surface velocities from satellite images.
IEEE Geoscience and Remote Sensing Letters, 4 (4), .
(doi:10.1109/LGRS.2007.900700).
Abstract
The knowledge of ocean surface circulation is of major
importance for many applications, including the understanding
of global climate, resources exploitation, and containment of
chemical spills. In this letter, sea-surface feature tracking based
on the Hopfield neural network (NN) is described. The method is
based on the minimization of an energy function that represents
the feature tracking problem. A Hopfield NN is used to merge
cross-correlation information with prior knowledge of sea-surface
flows and image contextual information. It has been tested on
real satellite images. A set of five Advanced Very High Resolution
Radiometer thermal images of the coastal zone of California, along with a data set of coincident surface drifters positions, was used to test the method. Results of the new analysis are compared within situ data and previous results using other techniques. The method can be used on various kinds of images for tracking and also find other applications in image registration and pattern recognition.
This record has no associated files available for download.
More information
Published date: October 2007
Additional Information:
In this paper the artificial intelligence technique developed by the authors and used by a number of researchers for a range of different applications over the past ten years was applied to satellite ocean data and compared for the first time with the results achieved using other techniques. The favourable results which have been reported in a number of international conferences are discussed.
Keywords:
feature extraction, hopfield networks, neural networks (NNs), sea surface, tracking.
Organisations:
Astronautics Group
Identifiers
Local EPrints ID: 49356
URI: http://eprints.soton.ac.uk/id/eprint/49356
ISSN: 1545-598X
PURE UUID: b5c4dfd0-3d44-4feb-bade-4d9df03747e2
Catalogue record
Date deposited: 01 Nov 2007
Last modified: 15 Mar 2024 09:55
Export record
Altmetrics
Contributors
Author:
S. Cote
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics