Date of Award
August 2020
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Division of Agriculture (SAFES)
Committee Member
John D Mueller
Committee Member
Michael T Plumblee
Committee Member
Michael W Marshall
Abstract
Multiple linear regression models were developed to predict sand and clay content along with soil organic matter content from RGB imagery from both commercially available satellite imagery as well as RGB UAV imagery. UAV Imagery was tested at two flight altitudes to determine if lower or higher altitude had an effect on prediction. In cases of sand, clay, and OM content, flight altitudes did not significantly differ in prediction abilities. Satellite imagery was evaluated using data from Planet Labs as well as Google Earth. Regression models were developed to predict sand, clay, and soil organic matter content from these satellite images, which captured fields with bare soil. An alternative to whole field data collection, referred to herein as the point sampling method, was introduced. A survey of currently available neural network and machine learning technologies was performed to establish which of these technologies could benefit the precision agriculture industry. A sample model was trained to detect and classify cotton blooms from low-altitude RGB imagery collected from a DJI Phantom 3 UAV.
Recommended Citation
Teddy, Brennan, "Novel Methods for RGB Aerial Image Analysis" (2020). All Theses. 3422.
https://tigerprints.clemson.edu/all_theses/3422