Regional mapping of spekboom canopy cover using very high resolution aerial imagery

Abstract

My sincere thanks to my supervisor, Adriaan van Niekerk, for his valuable technical input and guidance and for all the patient encouragement. Jan Vlok was instrumental in this research, and he is gratefully acknowledged for his vision, support and remarkable field expertise. Special thanks to Julie Verhulp, Raoul Duesimi and Aslam Parker of Chief Directorate: National Geospatial Information, for their generous provision of aerial imagery and related support. The Centre for Geographical Analysis, especially Garth Stephenson, Theo Pauw and Jascha Muller, graciously assisted with data, computing and software resources. Ilze Boonzaaier beautified some of the maps and Helene van Niekerk assisted with editing. Camera calibration software was kindly provided by Adrian Roos of Intergraph SA. Bernhard Jacobs of GeoSpace International assisted with valuable calibration discussions and data. Andrew Knipe, of the Gamtoos Irrigation Board, helped with funding administration. Finally, to Mireille van Reenen, for your moral support and great companythank you.

Biological Invasions and Ecological Restoration in South Africa

“…In assessing the outcomes, the potential of recent technologies should be considered for use, especially for scaling up implementation. These include specialised seed coatings, mechanised sowing, and aerial imagery (remote sensing, high resolution aerial imagery and drones; Dufour et al 2013;Zahawi et al 2015;Rebelo et al 2017;Harris et al 2018).…”

Texture Extraction Techniques for the Classification of Vegetation Species in Hyperspectral Imagery: Bag of Words Approach Based on Superpixels

“…However, in these works the only texture method considered was GLCM. Specifically, the authors of [10] present a classification scheme for the canopy cover mapping of spekboom in a large semiarid region in South Africa using multispectral imagery (red, green, blue, and near-infrared bands). Three classes were considered (spekboom, tree, and background) and the classification scheme is a decision tree with 47 features grouped into two broad categories: per-pixel (spectral information) and sliding window features (statistic of the pixels inside a small local neighborhood).…”

“…The simplest methods to characterize vegetation using textures are based on color histograms, statistical measures (mean, standard deviation, skewness, kurtosis, or entropy, among others), and clustered centers of filter bank responses. Following this approach, a classification scheme for the canopy cover mapping of spekboom in a large semiarid region in South Africa is presented in [10]. The scheme is based on a set of spectral features and vegetation indices, including several statistical measures in sliding windows of several sizes.…”

“…A classification scheme based on textures can be combined with other types of features obtained by UAVs to improve the classification results [10,16]. Among them are spectral features, vegetation indices, and morphological measures.…”

“…For the classification of a image using textures it is necessary to delimit regions over which the texture features are computed. Most of the vegetation classification methods proposed in the literature use regular patches [6,8,10,12,13,15,16,19]. In other cases, segmentation or object detection algorithms for dividing the image into regions are used [14,17,18].…”