Journal of Applied Remote SensingApproaching bathymetry estimation from high resolution multispectral satellite images using a neuro-fuzzy technique
|Format||Member Price||Non-Member Price|
|GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free.||Check Access|
This paper addresses bathymetry estimation from high resolution multispectral satellite images by proposing an accurate supervised method, based on a neuro-fuzzy approach. The method is applied to two Quickbird images of the same area, acquired in different years and meteorological conditions, and is validated using truth data. Performance is studied in different realistic situations of in situ data availability. The method allows to achieve a mean standard deviation of 36.7 cm for estimated water depths in the range [−18, −1] m. When only data collected along a closed path are used as a training set, a mean STD of 45 cm is obtained. The effect of both meteorological conditions and training set size reduction on the overall performance is also investigated.