A New Paper about UAV Mapping of Island Vegetation!
A new paper is just published in the Journal of International Journal of Applied Earth Observation and Geoinformation. The paper is entitled: "Evaluating techniques for mapping island vegetation from unmanned aerial vehicle (UAV) images: Pixel classification, visual interpretation and machine learning approaches".
Hamylton et al., 2020
They evaluate three approaches to mapping vegetation using images collected by an unmanned aerial vehicle (UAV) to monitor rehabilitation activities in the Five Islands Nature Reserve, Wollongong (Australia).
Three approaches to mapping vegetation were evaluated, including: (i) a pixel-based image classification algorithm applied to the composite spectral wavebands of the images collected, (ii) manual digitisation of vegetation directly from images based on visual interpretation, and (iii) the application of a machine learning algorithm, LeNet, based on a deep learning convolutional neural network (CNN) for detecting planted Lomandra tussocks.
The CNN approach emerged as a promising technique in this regard as it leveraged spatial information from the UAV images within the architecture of the learning framework by enforcing a local connectivity pattern between neurons of adjacent layers to incorporate the spatial relationships between features that comprised the shape of the Lomandra tussocks detected.
This publication is lead by S. M. Hamylton (The University of Wollongong, NSW, Australia), and our DU Marine Mapping Group member Rafael C. Carvalho contributed to the publication.
To read the full article, click here.