论文信息 - Cloud classification using support vector machines

Cloud classification using support vector machines

Cloud classification from GOES 8 (Geostationary Operational Environmental Satellite) imagery data is performed using the infrared (IR) channel only. For each block of the image, first and second order statistics are extracted and used to train and test a classifier. In this paper, cloud classification is performed using a support vector machine (SVM) classifier. This scheme, which is typically used to solve two-class problems, has been extended to classify ten different cloud and no-cloud areas. Preliminary results indicate the promise of this method for meteorological applications.

M.R. Azimi-Sadjadi | S.A. Zekavat | M. Azimi-Sadjadi | S. Zekavat | S. A. Zekavat

[1] Simon Haykin,et al. Neural Networks: A Comprehensive Foundation , 1998 .

[2] S. K. Sengupta,et al. Cloud field classification based upon high spatial resolution textural features: 1. Gray level co‐occurrence matrix approach , 1988 .

[3] Robert M. Haralick,et al. Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[4] Mahmood R. Azimi-Sadjadi,et al. Temporal updating scheme for probabilistic neural network with application to satellite cloud classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[5] S. Gunn. Support Vector Machines for Classification and Regression , 1998 .

[6] Johan A. K. Suykens,et al. Multiclass least squares support vector machines , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[7] Mahmood R. Azimi-Sadjadi,et al. A study of cloud classification with neural networks using spectral and textural features , 1999, IEEE Trans. Neural Networks.