Texture feature extraction by wavelet projection pursuit for cloud detection in AVIRIS and AVHRR imagery

Author

Bachmann, Charles M. ; Clothiaux, Eugene E.

Author_Institution

Airborne Radar Branch, Naval Res. Lab., Washington, DC, USA

fYear

1996

fDate

4-6 Sep 1996

Firstpage

351

Lastpage

360

Abstract

A constrained projection pursuit model is used to extract textural features from two multi-spectral, remote sensing databases of AVIRIS and AVHRR imagery. The goal is to evaluate methods which may eventually be useful for cloud detection in multi-angle imaging spectrometer (MISR) imagery. The method is an unsupervised adaptive wavelet technique that topologically constrains the projection vector and complements other techniques for extracting texture information

Keywords

clouds; feature extraction; image texture; multilayer perceptrons; object detection; remote sensing; search problems; unsupervised learning; visual databases; wavelet transforms; AVHRR imagery; AVIRIS imagery; cloud detection; constrained projection pursuit model; multi-angle imaging spectrometer imagery; multi-spectral remote sensing databases; texture feature extraction; unsupervised adaptive wavelet technique; wavelet projection pursuit; Airborne radar; Artificial neural networks; Brain modeling; Clouds; Cost function; Electronic mail; Feature extraction; High performance computing; Laboratories; Radar detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1996] VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop

Conference_Location

Kyoto

ISSN

1089-3555

Print_ISBN

0-7803-3550-3

Type

conf

DOI

10.1109/NNSP.1996.548365

Filename

548365