Spectral Signature Generalization and Expansion Can Improve the Accuracy of Satellite Image Classification

Alice G. Laborte, Aileen A. Maunahan, Robert J. Hijmans · 2010

Read Spectral Signature Generalization and Expansion Can Improve the Accuracy of Satellite Image Classification by Alice G. Laborte, Aileen A. Maunahan, Robert J. Hijmans (2010) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0010516.txt.

Description

Alice Laborte, Aileen Maunahan and Robert Hijmans showed how to improve satellite land maps by broadening their training data in PLOS ONE in 2010. Classifying satellite images usually trains on one image plus matching ground checks. Each land type gets a spectral signature, its fingerprint in light. Signatures from a single scene can fail elsewhere. The team compared that standard with methods using many images and wider signature sets.

Broader signatures classified new scenes more accurately. Better land maps feed farming, forestry, and disaster planning worldwide. Remote sensing is only as good as its ground truth and methods. This study offers a practical recipe for doing it better. It is a methods upgrade for a tool governments rely on.

Catalog record

CREATORAlice G. Laborte, Aileen A. Maunahan, Robert J. Hijmans
YEAR2010
COLLECTIONPAPERS
FORMATTXT
FILE SIZE34 KB
LICENSECreative Commons Attribution License
RIGHTSCC BY
SOURCEPLOS ONE

Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0010516

Browse the full library · About the Tower of Babel