An FFT-based algorithm for computation of Gabor transform with its application to cloud detection/classification

Author

Tian, Bin ; Azimi-Sadjadi, Mahmood R. ; Shaikh, Mukhtiar A. ; Vonder-Haar, Tom

Author_Institution

Dept. of Electr. Eng., Colorado State Univ., Fort Collins, CO, USA

Volume

2

fYear

1996

fDate

27-31 May 1996

Firstpage

1108

Abstract

An efficient algorithm for the computation of 2D discrete Gabor transform is introduced. Under the assumption of non-overlapping windows, which is satisfied in many practical cases, the 2D Gabor coefficients can be calculated through an FFT-based scheme. Combining with the Kohonen self-organized map, this method is used in a real-world problem dealing with cloud detection/classification. Simulation results are also provided which show the promise of the proposed method

Keywords

atmospheric techniques; clouds; fast Fourier transforms; geophysical signal processing; geophysics computing; image classification; remote sensing; self-organising feature maps; transforms; FFT-based algorithm; Kohonen self-organized map; algorithm; atmosphere; cloud detection; image classification; image processing; measurement technique; meteorology; neural net; remote sensing; two dimensional discrete Gabor transform; Atmosphere; Cloud computing; Discrete transforms; Equations; Feature extraction; Neural networks; Pipeline processing; Recurrent neural networks; Robustness; Tellurium;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1996. IGARSS '96. 'Remote Sensing for a Sustainable Future.', International

Conference_Location

Lincoln, NE

Print_ISBN

0-7803-3068-4

Type

conf

DOI

10.1109/IGARSS.1996.516583

Filename

516583