Abstract

We describe recent research into using the visual primitive of texture to analyze and manage large collections of remote sensed image and video data. Texture is regarded as the spatial dependence of pixel intensity. It is characterized by the amount of dependence at different scales and orientations, as measured with frequency-selective filters. A homogeneous texture descriptor based on the filter outputs is shown to enable (1) content-based image retrieval in large collections of satellite imagery, (2) semantic labeling and layout retrieval in an aerial video management system, and (3) statistical object modeling in geographic digital libraries.

© 2004 Optical Society of America

Hyperspectral remote sensing image retrieval system using spectral and texture features

Jing Zhang, Wenhao Geng, Xi Liang, Jiafeng Li, Li Zhuo, and Qianlan Zhou
Appl. Opt. 56(16) 4785-4796 (2017)

Methods for automatic target recognition by use of electro-optic sensors: introduction to the feature issue

Abhijit Mahalanobis and François Goudail
Appl. Opt. 43(2) 207-209 (2004)

Algorithm for the retrieval of columnar water vapor from hyperspectral remotely sensed data

Alessandro Barducci, Donatella Guzzi, Paolo Marcoionni, and Ivan Pippi
Appl. Opt. 43(29) 5552-5563 (2004)

Effective and efficient subjective testing of texture similarity metrics

Jana Zujovic, Thrasyvoulos N. Pappas, David L. Neuhoff, René van Egmond, and Huib de Ridder
J. Opt. Soc. Am. A 32(2) 329-342 (2015)

Improved technique for retrieval of forest parameters from hyperspectral remote sensing data

Vladimir V. Kozoderov, Egor V. Dmitriev, and Anton A. Sokolov
Opt. Express 23(24) A1342-A1353 (2015)