Using drone imagery and image segmentation techniques to automatically delineate individual apple trees

Drone imagery is often used to calculate vegetation indices such as the normalized difference vegetation index (NDVI) to characterize the condition of individual trees in orchards. Individual trees are often defined as a centroid (centre of the tree), or a circle (buffer around the centroid) or a rectangular area (plot). The NDVI values are then extracted for these entities [...]

Using drone imagery and image segmentation techniques to automatically delineate individual apple trees2021-02-12T14:24:46+02:00

Efficacy of machine learning and LiDAR data for crop type mapping

By Atman Prins Accurate crop type maps are important for obtaining agricultural statistics such as water use or harvest estimations. The traditional approach to obtaining maps of cultivated fields is by manually digitising the fields from satellite or aerial imagery. However, manual digitising is time-consuming, expensive and subject to human error. Automated remote sensing [...]

Efficacy of machine learning and LiDAR data for crop type mapping2023-01-23T08:34:13+02:00

TerraClim – StoryMap

  We are progressing well with the TerraClim project, and major milestone in the efficiency and accuracy of interpolations.The regional interpolation analysis divided the Western Cape study area into smaller regions using the local terrain and climatic characteristics of that particular region. The regionalisation of temperature interpolation showed improved accuracy of spatial interpolations by up [...]

TerraClim – StoryMap2021-02-08T17:56:05+02:00

Crop type mapping using LiDAR, Sentinel-2 and aerial imagery with machine learning algorithms

by Atman Prins The second experiment used the methods developed for the first experiment to perform a five-class classification. The five classes consisted of maize, cotton, groundnuts, orchards and non-agriculture. Sentinel-2 and aerial imagery data were added to the analysis and were compared to LiDAR data. The LiDAR data was obtained from a 2016 [...]

Crop type mapping using LiDAR, Sentinel-2 and aerial imagery with machine learning algorithms2021-02-09T11:47:18+02:00

CITRII – Burgersford Citrus Orchards

This video is a flyover showing the results of a satellite image (WorldView-2 dated 15 March 2020) analysis of a citrus orchard draped over the Digital Elevation Model of South Africa at 2m resolution (DEMSA2). The analysis was carried out for agricultural research and innovation business CITRII. The automated analysis developed by [...]

CITRII – Burgersford Citrus Orchards2020-12-14T10:06:00+02:00

VIDEO #03 | THE TERRACLIM PROJECT | WHAT’S NEXT?

Wynland has released part three of Winetech's flagship project, TerraClim, being undertaken by the CGA. For many wine grape producers in South Africa, access to accurate and detailed climate and GIS data is limited. Terraclim is funded by Winetech and is an online spatial decision-support system specifically [...]

VIDEO #03 | THE TERRACLIM PROJECT | WHAT’S NEXT?2020-06-12T13:56:11+02:00

Dense Point Cloud of Vineyard

This is a dense point cloud of a vineyard created with drone imagery with 4 bands (green, red ,red edge and near infrared). The imagery is displayed in false colour using the green , red and red edge bands. The dense point cloud was created using Agisoft Metashape and can be exported as a digital [...]

Dense Point Cloud of Vineyard2020-04-14T14:30:29+02:00

CGA and SASRI remote sensing in sugarcane research published

Prof Adriaan van Niekerk and Jascha Muller of the Centre for Geographical Analysis (CGA), and Dr Abraham Singels of the South African Sugarcane Research Institute (SASRI), have published their collaborative research assessing the use of multispectral remote sensing to determine fractional absorbed photosynthetically active radiation (fAPAR) in sugarcane. Crop growth models regularly use fAPAR as [...]

CGA and SASRI remote sensing in sugarcane research published2020-04-01T13:23:47+02:00

Assessing the ability of the Prometheus Fire Simulation Model to predict fire spread based on the 2018 George fire

By Lauren McCarthy Wildfires occur globally, destroying thousands of hectares of vegetation, affecting ecosystems, the environment, and humans. Fire spread models, based on fire behaviour algorithms, have been developed in different regions to aid researchers in better understanding fires and fire-management teams in fighting the fires and making important decisions. One such model is [...]

Assessing the ability of the Prometheus Fire Simulation Model to predict fire spread based on the 2018 George fire2020-02-14T08:36:58+02:00
Go to Top