S. Tadokoro, T. Nagao, M. Fukumi, and N. Akamatsu (Japan)
Neural Networks, Genetic Algorithms, SAR, Featureselection
In this paper, drift ice is detected in order to prevent marine accident in winter and improve reliability of sea data. The drift ice always has the necessity to observe thickness, speed and a course change with time. Then, the images are obtained from observation equipment (Synthetic Aperture Radar: SAR) installed satellite independent of weather conditions such as clouds. The drift ice in SAR images is undetectable using threshold that is linear processing [1][2]. Therefore, this paper aims at automatic detection of drift ice using NN (Neural Networks) effective in nonlinear processing[11]. Furthermore, GA (Genetic Algorithms) is used for reduction of the network size of NN and acquisition of the data that function effective in drift ice detection.
Important Links:
Go Back
