1 January 2011 Approaching bathymetry estimation from high resolution multispectral satellite images using a neuro-fuzzy technique
Author Affiliations +
Abstract
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.
© (2011) Society of Photo-Optical Instrumentation Engineers (SPIE)
Linda Corucci, Andrea Masini, Marco Cococcioni, "Approaching bathymetry estimation from high resolution multispectral satellite images using a neuro-fuzzy technique," Journal of Applied Remote Sensing 5(1), 053515 (1 January 2011). https://doi.org/10.1117/1.3569125 . Submission:
JOURNAL ARTICLE
16 PAGES


SHARE
Back to Top