Airborne Hyperspectral Remote Sensing for Identification Grassland Vegetation

Abstract

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.

Identification of roofing materials with Discriminant Function Analysis and Random Forest classifiers on pan-sharpened WorldView-2 imagery – a comparison

“…Consequently, while first studies attempted to classify aggregated land cover classes (e.g. forests, grasslands or artificial surfaces), nowadays it is possible to produce species-level habitat maps (Burai, P. et al 2015(Burai, P. et al , 2016Deák, M. et al 2017).…”

Estimating dry biomass and plant nitrogen concentration in pre-Alpine grasslands with low-cost UAS-borne multispectral data – a comparison of sensors, algorithms, and predictor sets

“…Together, these factors limit the reliability of spaceborne observations in mountainous areas. Airborne remote sensing data have occasionally been used in the past to match the required spatial scale and to explore the increased radiometric resolution of hyperspectral sensors (Atzberger et al, 2015;Burai et al, 2015;. But airborne data are still affected by the abovementioned weather-and topography-related challenges.…”

Species-level classification of urban trees from worldview-2 imagery in Debrecen, Hungary: an effective tool for planning a comprehensive green network to reduce dust pollution

“…Remote sensing techniques are nowadays widely used for urban vegetation mapping. Multispectral remote sensing is an effective and accessible tool to create thematic maps that are useful in urban management or spatial planning (Burai et al, 2015a). Satellite images are available to survey vegetation types and species-level distribution even in areas with limited accessibility.…”