Masters Degrees (Land Surveying)

Permanent URI for this collectionhttps://hdl.handle.net/10413/6850

Browse

Now showing 1 - 3 of 3

Change detection of invasive bracken fern (Pteridium aquilinum [L.] Kuhn) in the Royal Natal National Park and Rugged Glen Nature Reserve.
(2013) Singh, Kaveer.; Forbes, Angus Mcfarlane.; Akombelwa, Mulemwa.
Bracken fern (Pteridium aquilinum [L.] Kuhn) is an indigenous invasive plant and it is known to have a negative impact on biodiversity. This research focuses on infestations of bracken fern in two areas within the uKhahlamba Drakensberg Park World Heritage Site; the Royal Natal National Park and the Rugged Glen Nature Reserve. Prior change detection research on bracken fern were constrained due to the low resolution satellite imagery and the inability of hard classification techniques to account for the mixtures of land cover types that occur within pixels of low resolution imagery. To overcome these constraints this research applied the fuzzy image classification technique to multispectral digital aerial imagery of 0.5 m spatial resolution. Multi date imagery used for image classification was captured in the mid-winter of 2009 and mid-spring of 2011. Thereafter post-classification change detection analysis was conducted using the fuzzy classified images. The classified images were verified using ground truth surveys. The 2009 and 2011 fuzzy classified images produced overall accuracies of 81.4% and 94.4% with Kappa coefficients of 0.63 and 0.89 respectively. This research found that the distinct seasonal development pattern of bracken fern and the time of year imagery were captured were significant factors in its detection. As bracken fern was found to be more spectrally distinct in spring as compared to winter, due to the plant growth of bracken fern, grass and other shrubbery. These classified images were used in post-classification change detection analysis which revealed that the bracken fern infestation in the Royal Natal National Park and Rugged Glen Nature Reserve had increased at a rate of 24 % and 27 % per annum respectively. This showed that bracken fern is spreading in the Royal Natal National Park and Rugged Glen Nature Reserve, as expected. Fire regimes, slope and aspect were found as factors that could be promoting the spread of bracken fern, 67.5 % and 75 % of the bracken fern infestation in the Park and Reserve respectively, occurred in areas that were burnt by fire regimes and have gentle to moderately gentle slopes facing east, south east and south.
Machine learning, classification of 3D UAV-SFM point clouds in the University of KwaZulu-Natal (Howard College)
(2020) Ntuli, Simiso Siphenini.; Forbes, Angus Mcfarlane.
Three-dimensional (3D) point clouds derived using cost-effective and time-efficient photogrammetric technologies can provide information that can be utilized for decision-making in engineering, built environment and other related fields. This study focuses on the use of machine learning to automate the classification of points in a heterogeneous 3D scene situated in the University of KwaZulu-Natal, Howard College Campus sports field. The state of the camera mounted on the unmanned aerial vehicle (UAV) was evaluated through the process of camera calibration. Nadir aerial images captured using a UAV were used to generate a 3D point cloud employing the structure-from-motion (SfM) photogrammetric technique. The generated point cloud was georeferenced using natural ground control points (GCPs). Supervised and unsupervised classification approaches were used to classify points into three classes: ground, high vegetation and building. The supervised classification algorithm used a multi-scale dimensionality analysis to classify points. A georeferenced orthomosaic was used to generate random points for cross-validation. The accuracy of classification was evaluated, employing both qualitative and quantitative analysis. The camera calibration results showed negligible discrepancies when a comparison was made between the results obtained and the manufacturer’s specifications in parameters of the camera lens; hence the camera was in the excellent state of being used as a measuring device. Site visits and ground truth surveys were conducted to validate the classified point cloud. An overall root-mean-square (RMS) error of 0.053m was achieved from georeferencing the 3D point cloud. A root-mean-square error of 0.032m was achieved from georeferencing the orthomosaic. The multi-scale dimensionality analysis classified a point cloud and achieved an accuracy of 81.3% and a Kappa coefficient of 0.70. Good results were also achieved from the qualitative analysis. The classification results obtained indicated that a 3D heterogeneous scene can be classified into different land cover categories. These results show that the classification of 3D UAV-SfM point clouds provides a helpful tool for mapping and monitoring complex 3D environments.
The role of the geomaticist in natural resource management.
(2000) Fifield, Simon Peter.; Fourie, Clarissa.; Forbes, Angus Mcfarlane.
The essence of this thesis may be described by Ruther's argument that the survey profession is confronted with the necessity of having to redefine its role in society, or face the consequences of having the profession become marginalised (n .d: 1). The thesis reviews the functions of a traditional land surveyor, and shows how these functions are diminishing. This is done to illustrate the need for change in the profile of a traditional land surveyor, and the necessity of him redefining his role in society, in order to prosper in the future. The concept of geomatics, as an integrated approach to the acquisition and management of spatial data is introduced, and is used to illustrate the types of skills which a traditional land surveyor already has, and would need to acquire, in order to make the transition to a modern land surveyor, or what is tenned a geomaticist. A case study is then carried out in order to test the validity of the conceptual framework.

Browse

Browsing Masters Degrees (Land Surveying) by Author "Forbes, Angus Mcfarlane."