Rochester Institute of Technology
Comparison of Hyperspectral Imagery Target Detection Algorithm Chains
Abstract
dc:description.abstractDetection of a known target in an image has several different approaches. The complexity and number of steps involved in the target detection process makes a comparison of the different possible algorithm chains desirable. Of the different steps involved, some have a more significant impact than others on the final result the ability to find a target in an image. These more important steps often include atmospheric compensation, noise and dimensionality reduction, background characterization, and detection (matched filtering for this research). A brief overview of the algorithms to be compared for each step will be presented. This research seeks to identify the most effective set of algorithms for detecting a known tar get. Several different algorithms for each step will be presented, to include ELM, FLAASH, ACORN, MNF, PPI, N-FINDR, MAXD, and two matched filters that employ a structured background model OSP and ASD. The chains generated by these algorithms will be com pared using the Forest Radiance I HYDICE data set. Finally, ROC curves and AFAR values are calculated for each algorithm chain and a comparison of them is presented. Detection rates at a CFAR are also compared. Since a relatively small number of algorithms were used for each step, there were no definitive results generated. However, a comprehensive comparison of the chains using the above mentioned algorithms is presented.
Degree
thesis:*- Name thesis:degree_name
- Imaging Science (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Chester F. Carlson Center for Imaging Science (COS)
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Grimm, David C.
- Contributors dc:contributor
-
- John Schott
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/8138