Date of Award
Summer 2019
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical and Computer Engineering
First Advisor
Medeiros, Henry
Second Advisor
Tabb, Amy
Third Advisor
Ababei, Cristinel
Abstract
A key aspect to controlling and reducing the effects invasive insect specieshave on agriculture is to obtain knowledge about the migration patterns of thesespecies. Current state-of-the-art methods of studying these migration patternsinvolve a mark-release-recapture technique, in which insects are released afterbeing marked and researchers attempt to recapture them later. However, thisapproach involves a human researcher manually searching for these insects inlarge fields and results in very low recapture rates. This thesis proposes anautomated system for detecting released insects using an unmanned aerialvehicle. Our system utilizes ultraviolet lighting technology, digital cameras, andlightweight computer vision algorithms to more quickly and accurately detectinsects compared to the state of the art. The efficiency and accuracy that thissystem provides will allow for a more comprehensive understanding of invasiveinsect species migration patterns. Our experimental results demonstrate that oursystem can detect real target insects in field conditions with high precision andrecall rates. Additionally, insect GPS coordinates can be localized using an imagereprojection algorithm, resulting in a generated map of the test field with insectlocations.