Projection-based methods for hyperspectral image fraction estimation

In this paper, we investigate the issues that arise with the use of large spectral libraries in practical applications of fraction estimation in hyperspectral imaging. We then present a new technique for fraction estimation based on the method of successive projections onto convex sets. Results are...

Full description

Saved in:
Bibliographic Details
Published in1998 IEEE Southwest Symposium on Image Analysis and Interpretation (Cat. No.98EX165) pp. 244 - 249
Main Authors Triscari, J.M., Iverson, A.E., Sementilli, P.J., West, K.F.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1998
Subjects
Detectors
Hyperspectral imaging
Hyperspectral sensors
Intelligent vehicles
Libraries
Object detection
Pixel
Spatial resolution
Vectors
Vehicle detection
Online AccessGet full text

Cover

More Information
Summary:In this paper, we investigate the issues that arise with the use of large spectral libraries in practical applications of fraction estimation in hyperspectral imaging. We then present a new technique for fraction estimation based on the method of successive projections onto convex sets. Results are presented that demonstrate the ability of this technique to recover information that cannot be recovered using traditional techniques based on linear regression alone.
ISBN:0780348761
9780780348769
DOI:10.1109/IAI.1998.666893