Unsupervised hyperspectral band selection in the compressive sensing domain

Thumbnail Image

Files

109860A.pdf (1.92 MB)

Links to Files

https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10986/109860A/Unsupervised-hyperspectral-band-selection-in-the-compressive-sensing-domain/10.1117/12.2517439.full

Permanent Link

https://doi.org/10.1117/12.2517439
 http://hdl.handle.net/11603/14981

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

Date

2019-05-14

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Bernard Lampe, Adam Bekit, Charles Della Porta, Bai Xue, and Chein-I Chang "Unsupervised hyperspectral band selection in the compressive sensing domain", Proc. SPIE 10986, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV, 109860A (14 May 2019); https://doi.org/10.1117/12.2517439

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
© 2019 Society of Photo-Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.

Subjects

Data Reduction (DR)
Band Selection (BS)
Band Clustering (BC)
Compressive Sensing (CS)
Restricted Isometric Property (RIP)
Restricted Conformal Property (RCP)
Compressive Sensing Sampling Rate (CSSR)

Abstract

Band selection (BS) algorithms are an effective means of reducing the high volume of redundant data produced by the hundreds of contiguous spectral bands of Hyperspectral images (HSI). However, BS is a feature selection optimization problem and can be a computationally intensive to solve. Compressive sensing (CS) is a new minimally lossy data reduction (DR) technique used to acquire sparse signals using global, incoherent, and random projections. This new sampling paradigm can be implemented directly in the sensor acquiring undersampled, sparse images without further compression hardware. In addition, CS can be simulated as a DR technique after an HSI has been collected. This paper proposes a new combination of CS and BS using band clustering in the compressively sensed sample domain (CSSD). The new technique exploits the incoherent CS acquisition to develop BS via a CS transform utilizing inter-band similarity matrices and hierarchical clustering. It is shown that the CS principles of the restricted isometric property (RIP) and restricted conformal property (RCP) can be exploited in the novel algorithm coined compressive sensing band clustering (CSBC) which converges to the results computed using the original data space (ODS) given a sufficient compressive sensing sampling ratio (CSSR). The experimental results show the effectiveness of CSBC over traditional BS algorithms by saving significant computational space and time while maintaining accuracy.