Date of Award

Fall 2021

Document Type


Degree Name

Master of Science (MS)


Electrical and Computer Engineering

First Advisor

Medeiros, Henry P.

Second Advisor

Ababei, Cristinel

Third Advisor

Tabb, Amy


In this thesis, we use machine learning techniques to address limitations in our ability to monitor pest insect migrations. Invasive insect populations, such as the brown marmorated stink bug (BMSB), cause significant economic and environmental damages. In order to mitigate these damages, tracking BMSB migration is vital, but it also poses a challenge. The current state-of-the-art solution to track insect migrations is called mark-release-recapture. In mark-release-recapture, a researcher marks insects with a fluorescent powder, releases them back into the wild, and searches for the insects using ultra-violet flashlights at suspected migration destination locations. However, this involves a significant amount of labor and has a low recapture rate. By automating the insect search step, the recapture rate can be improved, reducing the amount of labor required in the process and improving the quality of the data. We propose a solution to the BMSB migration tracking problem using an unmanned aerial vehicle (UAV) to collect video data of the area of interest. Our system uses an ultra violet (UV) lighting array and digital cameras mounted on the bottom of the UAV, as well as artificial intelligence algorithms such as convolutional neural networks (CNN), and multiple hypotheses tracking (MHT) techniques. Specifically, we propose a novel computer vision method for insect detection using a Convolutional Variational Auto Encoder (CVAE). Our experimental results show that our system can detect BMSB with high precision and recall, outperforming the current state-of-the-art. Additionally, we associate insect observations using MHT, improving detection results and accurately counting real-world insects.

Included in

Engineering Commons