Title :
A multi-channel temporally adaptable system for continuous cloud classification from satellite imagery
Author :
Azimi-Sadjadi, M.R. ; Wang, J. ; Saitwal, K. ; Reinke, D.
Author_Institution :
Dept. of Electr. & Comput. Eng., Colorado State Univ., Fort Collins, CO, USA
Abstract :
A new multi-spectral scheme for cloud classification from satellite imagery is proposed which involves two temporally adaptable probabilistic neural networks, one for the visible and one for the infrared channels. This system offers the ability to perform continuous updating during the whole day. The results using five classes are provided which show the effectiveness of the proposed scheme
Keywords :
climatology; clouds; geophysics computing; image classification; neural nets; IR channels; climatology; cloud classification; probabilistic neural networks; satellite imagery; visible channel; Atmosphere; Clouds; Electronic mail; Estimation theory; Infrared imaging; Neural networks; Pattern recognition; Probability density function; Satellites; Temperature;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938404
