Header

UZH-Logo

Maintenance Infos

Determination of target detection limits in hyperspectral data using band selection and dimensionality reduction


Gross, Wolfgang; Böhler, Jonas; Twizer, Kfir; Kedem, Bar; Lenz, Andreas; Kneubühler, Mathias; Wellig, Peter; Oechslin, Roland; Schilling, Hendrik; Rotman, Stanley R; Middelmann, Wolfgang (2016). Determination of target detection limits in hyperspectral data using band selection and dimensionality reduction. In: Target and Background Signatures II, Edinburgh, 26 September 2016 - 27 September 2016, 99970H.

Abstract

Hyperspectral remote sensing data can be used for civil and military applications to robustly detect and classify"
"target objects. High spectral resolution of hyperspectral data can compensate for the comparatively low spatial resolution, which allows for detection and classification of small targets, even below image resolution. Hyper- spectral data sets are prone to considerable spectral redundancy, affecting and limiting data processing and algorithm performance. As a consequence, data reduction strategies become increasingly important, especially in view of near-real-time data analysis. The goal of this paper is to analyze different strategies for hyperspectral band selection algorithms and their effect on subpixel classification for different target and background mate- rials. Airborne hyperspectral data is used in combination with linear target simulation procedures to create a representative amount of target-to-background ratios for evaluation of detection limits. Data from two different airborne hyperspectral sensors, AISA Eagle & Hawk, are used to evaluate transferability of band selection when using different sensors. The same target objects were recorded to compare the calculated detection limits. To determine subpixel classification results, pure pixels from the target materials are extracted and used to simulate mixed pixels with selected background materials. Target signatures are linearly combined with different back- ground materials in varying ratios. The commonly used classification algorithms Adaptive Coherence Estimator (ACE) is used to compare the detection limit for the original data with several band selection and data reduction strategies. The evaluation of the classification results is done by assuming a fixed false alarm ratio and calcu- lating the mean target-to-background ratio of correctly detected pixels. The results allow drawing conclusions about specific band combinations for certain target and background combinations. Additionally, generally useful wavelength ranges are determined and the optimal amount of principal components is analyzed.

Abstract

Hyperspectral remote sensing data can be used for civil and military applications to robustly detect and classify"
"target objects. High spectral resolution of hyperspectral data can compensate for the comparatively low spatial resolution, which allows for detection and classification of small targets, even below image resolution. Hyper- spectral data sets are prone to considerable spectral redundancy, affecting and limiting data processing and algorithm performance. As a consequence, data reduction strategies become increasingly important, especially in view of near-real-time data analysis. The goal of this paper is to analyze different strategies for hyperspectral band selection algorithms and their effect on subpixel classification for different target and background mate- rials. Airborne hyperspectral data is used in combination with linear target simulation procedures to create a representative amount of target-to-background ratios for evaluation of detection limits. Data from two different airborne hyperspectral sensors, AISA Eagle & Hawk, are used to evaluate transferability of band selection when using different sensors. The same target objects were recorded to compare the calculated detection limits. To determine subpixel classification results, pure pixels from the target materials are extracted and used to simulate mixed pixels with selected background materials. Target signatures are linearly combined with different back- ground materials in varying ratios. The commonly used classification algorithms Adaptive Coherence Estimator (ACE) is used to compare the detection limit for the original data with several band selection and data reduction strategies. The evaluation of the classification results is done by assuming a fixed false alarm ratio and calcu- lating the mean target-to-background ratio of correctly detected pixels. The results allow drawing conclusions about specific band combinations for certain target and background combinations. Additionally, generally useful wavelength ranges are determined and the optimal amount of principal components is analyzed.

Statistics

Altmetrics

Downloads

47 downloads since deposited on 11 Nov 2016
47 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Event End Date:27 September 2016
Deposited On:11 Nov 2016 09:10
Last Modified:01 Sep 2017 06:15
Publisher:SPIE - International Society for Optical Engineering
Series Name:Proceedings of SPIE
Number:9997
ISSN:0277-786X
Free access at:Official URL. An embargo period may apply.
Publisher DOI:https://doi.org/10.1117/12.2240931
Official URL:http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2575999

Download

Download PDF  'Determination of target detection limits in hyperspectral data using band selection and dimensionality reduction'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 484kB
View at publisher