Evaluation of oil thickness by neural network analysis of IR imagery

摘要

Neural network analysis of conventional thermal infra-red data gathered from surveillance aircraft was undertaken in order to evaluate if this approach can be used to determine the thickness of oil at sea. A Multi-Layer Perceptron meural netowrk architecture was sued to examine sea trial data and incidated that the best configuration for the prediction of oil thickness used the following core input variables: oil brightness, time of day, sea brightness, wind speed, oil type and sea temperature.