Author :
Vidal-Fernandez, Eva ; Piedra-Fernandez, Jose A. ; Almendros-Jimenez, Jesus M. ; Canton-Garbin, Manuel
Author_Institution :
Dept. of Inf., Univ. of Almeria, Almeria, Spain
Abstract :
The ocean covers over 70% of the surface of our planet and plays a key role in the global climate. Most ocean circulation is mesoscale (scales of 50-500 km and 10-100 days), and the energy in mesoscale circulation is at least one order of magnitude greater than general circulation; therefore, the study of mesoscale oceanic structures (MOS) is crucial to ocean dynamics, making it especially useful for analyzing global changes. The detection of MOS, such as upwellings or eddies, from satellites images is significant for marine environmental studies and coastal resource management. In this paper, we present an object-based image analysis (OBIA) system which segments and classifies regions contained in sea-viewing field-of-view sensor (SeaWiFS) and Moderate Resolution Imaging Spectro-radiometer (MODIS)-Aqua sensor satellite images into MOS. After color clustering and hierarchical data format (HDF) file processing, the OBIA system segments images and extracts image descriptors, producing primary regions. Then, it merges regions, recalculating image descriptors for MOS identification and definition. First, regions are labeled by a human-expert, who identifies MOS: upwellings, eddies, cool, and warm eddies. Labeled regions are then classified by learning algorithms (i.e., decision tree, Bayesian network, artificial neural network, genetic algorithm, and near neighbor algorithm) from selected features. Finally, the OBIA system enables images to be queried from the user interface and retrieved by means of fuzzy descriptors and oceanic structures. We tested our system with images from the Canary Islands and the North West African coast.
Keywords :
artificial satellites; belief networks; decision trees; feature extraction; feature selection; genetic algorithms; geophysics computing; image segmentation; neural nets; object tracking; oceanographic techniques; oceanography; radiometers; radiometry; remote sensing; Bayesian network algorithm; Canary island images; HDF file processing; MODIS-Aqua sensor satellite images; MOS detection; MOS identification; OBIA system-based image descriptor extraction; OBIA system-based image segmentation; OBIA system-based region classification; SeaWiFS images; artificial neural network algorithm; coastal resource management; color clustering data format file processing; cool eddy identification; decision tree algorithm; distance 50.00 km to 500.00 km; feature selection; fuzzy descriptors; general circulation energy magnitude; genetic algorithm; global change analysis; global climate; hierarchical data format file processing; image descriptor recalculation; labeled region classification; learning algorithms; mesoscale ocean circulation; mesoscale oceanic structure detection; mesoscale oceanic structure identification; moderate resolution imaging spectroradiometer; near neighbor algorithm; northwest African coast images; object-based image analysis system; ocean circulation energy magnitude; ocean dynamics; primary region merging; region labeling; satellite-based eddy detection; satellite-based upwelling detection; sea-viewing field-of-view sensor; time 10.00 day to 100.00 day; upwelling identification; user interface-queried images; user interface-retrieved images; warm eddy identification; Image color analysis; Image segmentation; Merging; Ocean temperature; Ontologies; Satellites; Automatic recognition; fuzzy logic; image retrieval; moderate resolution imaging spectro-radiometer (MODIS); object-based image analysis (OBIA); ocean satellite images; sea-viewing field-of-view sensor (SeaWiFS);
