The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XL-3/W3
https://doi.org/10.5194/isprsarchives-XL-3-W3-427-2015
https://doi.org/10.5194/isprsarchives-XL-3-W3-427-2015
19 Aug 2015
 | 19 Aug 2015

AIRBORNE HYPERSPECTRAL REMOTE SENSING FOR IDENTIFICATION GRASSLAND VEGETATION

P. Burai, T. Tomor, L. Bekő, and B. Deák

Keywords: Vegetation Mapping, Hyperspectral, Image Classification, Maximum Likelihood Classifier, Random Forest, Support Vector Machine, Open Landscape

Abstract. In our study we classified grassland vegetation types of an alkali landscape (Eastern Hungary), using different image classification methods for hyperspectral data. Our aim was to test the applicability of hyperspectral data in this complex system using various image classification methods. To reach the highest classification accuracy, we compared the performance of traditional image classifiers, machine learning algorithm, feature extraction (MNF-transformation) and various sizes of training dataset. Hyperspectral images were acquired by an AISA EAGLE II hyperspectral sensor of 128 contiguous bands (400–1000 nm), a spectral sampling of 5 nm bandwidth and a ground pixel size of 1 m. We used twenty vegetation classes which were compiled based on the characteristic dominant species, canopy height, and total vegetation cover. Image classification was applied to the original and MNF (minimum noise fraction) transformed dataset using various training sample sizes between 10 and 30 pixels. In the case of the original bands, both SVM and RF classifiers provided high accuracy for almost all classes irrespectively of the number of the training pixels. We found that SVM and RF produced the best accuracy with the first nine MNF transformed bands. Our results suggest that in complex open landscapes, application of SVM can be a feasible solution, as this method provides higher accuracies compared to RF and MLC. SVM was not sensitive for the size of the training samples, which makes it an adequate tool for cases when the available number of training pixels are limited for some classes.