Thesis Defense Announcement for Samantha Butler — 10/20/2021 at 11:15am

September 30, 2021

Candidate: Samantha Butler

Degree: M.S., Electrical & Computer Engineering

Thesis Title: Evaluation of Hyperspectral Band Selection Techniques for Real-Time Applications

Date and time: Wednesday, October 20th, 2021 at 11:15 AM

Venue: On-line Meeting via Webex –


Dr. Ali C. Gurbuz
Assistant Professor of Electrical and Computer Engineering
(Major Professor)

Dr. Mehmet Kurum
Assistant Professor of Electrical and Computer Engineering
(Committee Member)

Dr. John E. Ball
Associate Professor of Electrical and Computer Engineering
(Committee Member)

Dr. Stanton R. Price
U.S. Army Engineer Research and Development Center
(Committee Member)

Processing hyperspectral image data can be computationally expensive and difficult to employ for real-time applications due to its extensive spatial and spectral information. Further, applications in which computational resources may be limited can be hindered by the volume of data that is common with airborne hyperspectral image data. This paper proposes utilizing band selection to down-select the number of spectral bands to consider for a given classification task such that classification can be done at the edge. Specifically, we consider the following band selection techniques: FVGBS, MVPCA, ISSC, and NC-OC-MVPCA, to investigate their feasibility at identifying discriminative bands such that classification performance is not drastically hindered. This would greatly benefit applications where time-sensitive solutions are needed to ensure optimal outcomes. In this research, an NVIDIA AGX Xavier module is used as the edge device to run trained models on a simulated deployed unmanned aerial system. Classification performance of the proposed approach is measured in terms of classification accuracy and run time.

Best Regards,