Title :
Measuring the complexity of the ocean floor
Author :
Sams, T. ; Stage, B. ; Agerkvist, F.T. ; Christensen, T.
Author_Institution :
Danish Defence Res. Establ., Copenhagen, Denmark
Abstract :
In an attempt to classify the complexity of the ocean floor, we suggest a neural network-based algorithm which predicts a pixel based on its surroundings. The mean square of the difference between the original sidescan sonar image and the predicted image is then used as a measure of the complexity of the image
Keywords :
bathymetry; geophysical signal processing; military computing; naval engineering computing; neural nets; seafloor phenomena; sonar imaging; mean square difference; neural network-based algorithm; ocean floor complexity measurement; pixel prediction; predicted image; sidescan sonar image; Feedforward neural networks; Joining processes; Marine vehicles; Neural networks; Nonlinear filters; Oceans; Optical propagation; Prediction algorithms; Sea measurements; Sonar measurements;
Conference_Titel :
Neural Networks for Signal Processing X, 2000. Proceedings of the 2000 IEEE Signal Processing Society Workshop
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6278-0
DOI :
10.1109/NNSP.2000.890136
