Mapping Seabed Geology by Ground-Truthed Textural Image/Neural Network Classification of Acoustic Backscatter Mosaics

We present a novel, automated method for seabed classification based on shallow water backscatter mosaics from Sydney Harbour. Our approach compares the results between two different methods of image feature extraction when combined with artificial neural networks. The association of image textures with seabed geology is used to train the artificial neural networks to recognise the variability of textural attributes for three seabed classes comprising mud, sand and gravel. After network training, we classify unknown portions of the backscatter mosaic with a success rate ranging from 77% to 92%. Our results suggest that the computationally fast grey-level co-occurrence iteration algorithm holds promise for benthic habitat mapping in space and time, leading to real-time data analysis at sea.