Methodology for hyperspectral band and classification model selection

P. Groves, P. Bajcsy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Feature selection is one of the fundamental problems in nearly every application of statistical modeling, and hyperspectral data analysis is no exception. We propose a new methodology for combining unsupervised and supervised methods under classification accuracy and computational requirement constraints. It is designed to perform not only hyperspectral band (wavelength range) selection but also classification method selection. The procedure involves ranking hands based on information content and redundancy and evaluating a varying number of the top ranked bands. We term this technique Rank Ordered With Accuracy Selection (ROWAS). It provides a good tradeoff between feature space exploration and computational efficiency. To verify our methodology, we conducted experiments with a georeferenced hyperspectral image (acquired by an AVIRIS sensor) and categorical ground measurements.

Original languageEnglish (US)
Title of host publication2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages120-128
Number of pages9
ISBN (Electronic)0780383508, 9780780383500
DOIs
StatePublished - 2004
Event2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data - Greenbelt, United States
Duration: Oct 27 2003Oct 28 2003

Publication series

Name2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data

Conference

Conference2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data
CountryUnited States
CityGreenbelt
Period10/27/0310/28/03

ASJC Scopus subject areas

  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Methodology for hyperspectral band and classification model selection'. Together they form a unique fingerprint.

Cite this