Supervised band selection for optimal use of data from airborne hyperspectral sensors


Riedmann, M. and Milton, E.J. (2003) Supervised band selection for optimal use of data from airborne hyperspectral sensors In IGARSS '03 Proceedings of the International Geoscience and Remote Sensing Symposium, 21-25 July 2003, Toulouse, France. Institute of Electrical and Electronics Engineers (IEEE)., pp. 1770-1772.

Download

[img] PDF Riedmann_Milton_2003copyright.pdf - Other
Download (32kB)

Description/Abstract

This paper presents a practical supervised band selection procedure for airborne imaging spectrometers and Maximum Likelihood classification (MLC) as data application. The output band set is optimal in band location, width and number regarding the MLC accuracy of the classification task. The supervised algorithm is based on feature selection and requires a user-defined class set. For two given semi-natural vegetation data and class sets, the selected band sets performed superior to established vegetation band sets used in current satellite and airborne sensors, most noticeably for the first few bands. The algorithm was implemented in IDLTM/ENVITM. It may also be used for feature selection, the generation of classdiscriminate colour composites, the prioritization of already existing band sets, and the determination of the intrinsic discriminant dimensionality of the data set.

Item Type: Conference or Workshop Item (Paper)
Additional Information: CD-ROM
Venue - Dates: Proceedings of the International Geoscience and Remote Sensing Symposium (IGARSS), 2003-07-21 - 2003-07-25
Related URLs:
Subjects:
ePrint ID: 6175
Date :
Date Event
2003Published
Date Deposited: 21 May 2004
Last Modified: 17 Apr 2017 00:09
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/6175

Actions (login required)

View Item View Item