Header

UZH-Logo

Maintenance Infos

Optimal structural and spectral features for tree species classification using combined airborne laser scanning and hyperspectral data


Torabzadeh, Hossein; Leiterer, Reik; Schaepman, Michael E; Morsdorf, Felix (2015). Optimal structural and spectral features for tree species classification using combined airborne laser scanning and hyperspectral data. In: Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, Milan, Italy, 26 July 2015 - 31 July 2015, 5399-5402.

Abstract

In this paper, the performance of feature selection in tree species classification based on multi source earth observation data was studied. We applied a sequential forward floating feature selection on imaging spectroscopy (IS) and airborne laser scanning (ALS) data, as well as their combination. Qualitative comparison of the fused results shows that the selected spectral features are more distributed across the spectrum, in contrast to an accumulation of features in the near infrared region when using IS alone. A support vector machine (SVM) classifier was used for quantitative comparison of the different datasets. Assessing the classification accuracies confirmed the superiority of the selected subset of spectral and structural features compared to using all available features (improvement of > 7% in kappa accuracy).

Abstract

In this paper, the performance of feature selection in tree species classification based on multi source earth observation data was studied. We applied a sequential forward floating feature selection on imaging spectroscopy (IS) and airborne laser scanning (ALS) data, as well as their combination. Qualitative comparison of the fused results shows that the selected spectral features are more distributed across the spectrum, in contrast to an accumulation of features in the near infrared region when using IS alone. A support vector machine (SVM) classifier was used for quantitative comparison of the different datasets. Assessing the classification accuracies confirmed the superiority of the selected subset of spectral and structural features compared to using all available features (improvement of > 7% in kappa accuracy).

Statistics

Citations

Dimensions.ai Metrics
2 citations in Web of Science®
2 citations in Scopus®
1 citation in Microsoft Academic
Google Scholar™

Altmetrics

Downloads

43 downloads since deposited on 18 Dec 2015
15 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Event End Date:31 July 2015
Deposited On:18 Dec 2015 11:44
Last Modified:24 May 2018 05:09
Publisher:IEEE
OA Status:Green
Publisher DOI:https://doi.org/10.1109/igarss.2015.7327056

Download

Download PDF  'Optimal structural and spectral features for tree species classification using combined airborne laser scanning and hyperspectral data'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 330kB
View at publisher