Feature selection in AVHRR ocean satellite images by means of filter methods

Jose A. Piedra-Fernández, Manuel Cantón-Garbín, James Wang

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Automatic retrieval and interpretation of satellite images is critical for managing the enormous volume of environmental remote sensing data available today. It is particularly useful in oceanography and climate studies for examination of the spatio-temporal evolution of mesoscalar ocean structures appearing in the satellite images taken by visible, infrared, and radar sensors. This is because they change so quickly and several images of the same place can be acquired at different times within the same day. This paper describes the use of filter measures and the Bayesian networks to reduce the number of irrelevant features necessary for ocean structure recognition in satellite images, thereby improving the overall interpretation system performance and reducing the computational time. We present our results for the National Oceanographic and Atmospheric Administration satellite Advanced Very High Resolution Radiometer (AVHRR) images. We have automatically detected and located mesoscale ocean phenomena of interest in our study area (NorthEast Atlantic and the Mediterranean), such as upwellings, eddies, and island wakes, using an automatic selection methodology which reduces the features used for description by about 80%. Finally, Bayesian network classifiers are used to assess classification quality. Knowledge about these structures is represented with numeric and nonnumeric features.

Original languageEnglish (US)
Article number5508399
Pages (from-to)4193-4203
Number of pages11
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume48
Issue number12
DOIs
StatePublished - Dec 1 2010

Fingerprint

Advanced very high resolution radiometers (AVHRR)
AVHRR
Feature extraction
Satellites
filter
Ocean structures
ocean
Bayesian networks
temporal evolution
oceanography
Oceanography
eddy
upwelling
radar
sensor
remote sensing
Remote sensing
Radar
Classifiers
methodology

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

Cite this

Piedra-Fernández, Jose A. ; Cantón-Garbín, Manuel ; Wang, James. / Feature selection in AVHRR ocean satellite images by means of filter methods. In: IEEE Transactions on Geoscience and Remote Sensing. 2010 ; Vol. 48, No. 12. pp. 4193-4203.
@article{d9aa5e1017e14171a6296993a66ab29a,
title = "Feature selection in AVHRR ocean satellite images by means of filter methods",
abstract = "Automatic retrieval and interpretation of satellite images is critical for managing the enormous volume of environmental remote sensing data available today. It is particularly useful in oceanography and climate studies for examination of the spatio-temporal evolution of mesoscalar ocean structures appearing in the satellite images taken by visible, infrared, and radar sensors. This is because they change so quickly and several images of the same place can be acquired at different times within the same day. This paper describes the use of filter measures and the Bayesian networks to reduce the number of irrelevant features necessary for ocean structure recognition in satellite images, thereby improving the overall interpretation system performance and reducing the computational time. We present our results for the National Oceanographic and Atmospheric Administration satellite Advanced Very High Resolution Radiometer (AVHRR) images. We have automatically detected and located mesoscale ocean phenomena of interest in our study area (NorthEast Atlantic and the Mediterranean), such as upwellings, eddies, and island wakes, using an automatic selection methodology which reduces the features used for description by about 80{\%}. Finally, Bayesian network classifiers are used to assess classification quality. Knowledge about these structures is represented with numeric and nonnumeric features.",
author = "Piedra-Fern{\'a}ndez, {Jose A.} and Manuel Cant{\'o}n-Garb{\'i}n and James Wang",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/TGRS.2010.2050067",
language = "English (US)",
volume = "48",
pages = "4193--4203",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

Feature selection in AVHRR ocean satellite images by means of filter methods. / Piedra-Fernández, Jose A.; Cantón-Garbín, Manuel; Wang, James.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 48, No. 12, 5508399, 01.12.2010, p. 4193-4203.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Feature selection in AVHRR ocean satellite images by means of filter methods

AU - Piedra-Fernández, Jose A.

AU - Cantón-Garbín, Manuel

AU - Wang, James

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Automatic retrieval and interpretation of satellite images is critical for managing the enormous volume of environmental remote sensing data available today. It is particularly useful in oceanography and climate studies for examination of the spatio-temporal evolution of mesoscalar ocean structures appearing in the satellite images taken by visible, infrared, and radar sensors. This is because they change so quickly and several images of the same place can be acquired at different times within the same day. This paper describes the use of filter measures and the Bayesian networks to reduce the number of irrelevant features necessary for ocean structure recognition in satellite images, thereby improving the overall interpretation system performance and reducing the computational time. We present our results for the National Oceanographic and Atmospheric Administration satellite Advanced Very High Resolution Radiometer (AVHRR) images. We have automatically detected and located mesoscale ocean phenomena of interest in our study area (NorthEast Atlantic and the Mediterranean), such as upwellings, eddies, and island wakes, using an automatic selection methodology which reduces the features used for description by about 80%. Finally, Bayesian network classifiers are used to assess classification quality. Knowledge about these structures is represented with numeric and nonnumeric features.

AB - Automatic retrieval and interpretation of satellite images is critical for managing the enormous volume of environmental remote sensing data available today. It is particularly useful in oceanography and climate studies for examination of the spatio-temporal evolution of mesoscalar ocean structures appearing in the satellite images taken by visible, infrared, and radar sensors. This is because they change so quickly and several images of the same place can be acquired at different times within the same day. This paper describes the use of filter measures and the Bayesian networks to reduce the number of irrelevant features necessary for ocean structure recognition in satellite images, thereby improving the overall interpretation system performance and reducing the computational time. We present our results for the National Oceanographic and Atmospheric Administration satellite Advanced Very High Resolution Radiometer (AVHRR) images. We have automatically detected and located mesoscale ocean phenomena of interest in our study area (NorthEast Atlantic and the Mediterranean), such as upwellings, eddies, and island wakes, using an automatic selection methodology which reduces the features used for description by about 80%. Finally, Bayesian network classifiers are used to assess classification quality. Knowledge about these structures is represented with numeric and nonnumeric features.

UR - http://www.scopus.com/inward/record.url?scp=78649328357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649328357&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2010.2050067

DO - 10.1109/TGRS.2010.2050067

M3 - Article

VL - 48

SP - 4193

EP - 4203

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 12

M1 - 5508399

ER -