Automatic feature extraction from multisensorial oceanographic imagery

Abstract

The problem of identifying mesoscale structures has been studied using a variety of image processing techniques, mainly, texture analysis, edge detection, mathematical morphology, neural networks and wavelet transform. The foremost difficulties encountered in the preceding approaches are the presence of noise, mainly due to clouds and other atmospheric phenomena; the fact that gradients are weak and provide excess of information; the strong morphological variation that impedes an accurate geometric representation and the absence of a valid analytical model for the structures. In this context, the proposed methodology, due to its region-based nature, overcomes the edge detection inconveniences and obtains the proper structure identification. This automatic technique has been applied to the detection and feature extraction of coastal upwellings and filaments in the northwest African coast and the Alboran Sea using imagery from the AVHRR/2&3, SeaWiFS and MODIS sensors. The system has proven to be very effective and robust in a wide variety of climate conditions.