Publication:
Spatial low-rank tensor factorization for hyperspectral image unmixing

dc.contributor.advisor Manian, Vidya
dc.contributor.author Navas-Auger, William J.
dc.contributor.college College of Engineering en_US
dc.contributor.committee Sierra, Heidy
dc.contributor.committee Rivera Gallego, Wilson
dc.contributor.committee Arzuaga Cruz, Emmanuel
dc.contributor.department Department of Computer Science and Engineering en_US
dc.contributor.representative Romero Oliveras, Juan R.
dc.date.accessioned 2021-06-03T14:57:23Z
dc.date.available 2021-06-03T14:57:23Z
dc.date.issued 2021-05-14
dc.description.abstract This work presents a method for hyperspectral image unmixing based on nonnegative tensor factorization. While traditional approaches may process spectral information without regard for spatial structures in the data set, tensor factorization preserves the spectral-spatial relationship which we intend to exploit. We used a rank-(L, L, 1) decomposition which approximates the original tensor as a sum of R components. Each component is a tensor resulting from the multiplication of a low-rank spatial representation and a spectral vector. Our approach uses the spatial factors, to identify high abundance areas where pure pixels (endmembers) may lie. Finally, abundance maps are generated by applying Fully Constrained Least Squares for each inferred endmember. Results of this method are compared against other approaches based on non-negative matrix and tensor factorization. We observed a significant reduction of spectral angle distance for extracted endmembers and equal or better root mean square error for abundance maps as compared with existing benchmarks. en_US
dc.description.abstract Este trabajo presenta un método para desmezclar imágenes hiperespectrales basado en factorización de tensores no negativos. Mientras que los métodos tradicionales procesan información espectral sin tomar en consideración las estructuras espaciales en el conjunto de datos, la factorización tensorial conserva la relación espectral-espacial que pretendemos explorar y utilizar. En nuestro trabajo utilizamos una descomposición de rango-(L, L, 1) que se aproxima al tensor original como una suma de R componentes. Cada componente es un tensor resultante de la multiplicación de una representación espacial de bajo rango y un vector espectral. Nuestro enfoque utiliza los factores espaciales para identificar áreas de alta abundancia donde pueden encontrarse pıxeles puros. Finalmente, se generan mapas de abundancia usando ”Fully Constrained Least Squares” para cada pıxel puro inferido. Los resultados de este método se comparan con otros enfoques basados en matrices no negativas y factorizaciones de tensores. Observamos una reducción de la distancia del ángulo espectral para los pıxeles puros extraıdos y un error igual o menor error (RMSE) para los mapas de abundancia en comparación con el punto de referencia existente. en_US
dc.description.graduationSemester Spring en_US
dc.description.graduationYear 2021 en_US
dc.identifier.uri https://hdl.handle.net/20.500.11801/2772
dc.language.iso en en_US
dc.rights Attribution 3.0 United States *
dc.rights.holder (c) 2021 William J. Navas-Auger en_US
dc.rights.uri http://creativecommons.org/licenses/by/3.0/us/ *
dc.subject Remote Sensing en_US
dc.subject Non-negative Tensor Factorization en_US
dc.subject Hyperspectral Unmixing en_US
dc.subject Low-Rank en_US
dc.subject Signal Separation en_US
dc.subject.lcsh Spectral imaging en_US
dc.subject.lcsh Remote sensing en_US
dc.subject.lcsh Calculus of tensors en_US
dc.subject.lcsh Factorization (Mathematics) en_US
dc.subject.lcsh Vector processing (Computer science) en_US
dc.subject.lcsh Spatial analysis (Statistics) en_US
dc.title Spatial low-rank tensor factorization for hyperspectral image unmixing en_US
dc.type Dissertation en_US
dspace.entity.type Publication
thesis.degree.discipline Computing and Information Sciences and Engineering en_US
thesis.degree.level Ph.D. en_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
CIIC_NavasAugerWJ_2021
Size:
8.07 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: