Spectral unmixing of remotely sensed imagery using maximum entropy

Samir R. Chettri; Nathan S. Netanyahu

doi:10.1117/12.267839

26 February 1997 Spectral unmixing of remotely sensed imagery using maximum entropy

Samir R. Chettri, Nathan S. Netanyahu

Proceedings Volume 2962, 25th AIPR Workshop: Emerging Applications of Computer Vision; (1997) https://doi.org/10.1117/12.267839
Event: 25th Annual AIPR Workshop on Emerging Applications of Computer Vision, 1996, Washington, DC, United States

Abstract

This paper addresses the importance of a maximum entropy formulation for the extraction of content from a single picture element in a remotely sensed image. Most conventional classifiers assume a winner take all procedure in assigning classes to a pixel whereas in general it is the case that there exists more than one class within the picture element. There have been attempts to perform spectral unmixing using variants of least-squares techniques, but these suffer from conceptual and numerical problems which include the possibility that negative fractions of ground cover classes may be returned by the procedure. In contrast, a maximum entropy (MAXENT) based approach for sub-pixel content extraction possesses the useful information theoretic property of not assuming more information than is given, while automatically guaranteeing positive fractions. In this paper we apply MAXENT to obtain the fractions of ground cover classes present in a pixel and show its clear numerical superiority over conventional methods. The optimality of this method stems from the combinatorial properties of the information theoretic entropy.

Citation Download Citation

Samir R. Chettri and Nathan S. Netanyahu "Spectral unmixing of remotely sensed imagery using maximum entropy", Proc. SPIE 2962, 25th AIPR Workshop: Emerging Applications of Computer Vision, (26 February 1997); https://doi.org/10.1117/12.267839

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available