Research Focus
Develop computer vision techniques to address pressing problems in ecology in collaboration with domain experts. We have identified three exciting potential projects: (1) Species Distribution Mapping: This project aims to use computer vision techniques to map species distributions using citizen science and remote sensing data; (2) Camera-Trap Imagery Analysis: This project focuses on developing a system for detecting and classifying animals in camera-trap imagery, extending an existing automated classification model for the St. Louis region; and (3) Forest Canopy Structure Monitoring: This project aims to develop computer vision algorithms that integrate imagery from various remote sensing sources to understand the spatial distribution of trees and canopy structure. The exact project will be determined through discussion with the mentoring team. The targeted output of each project includes a public software repository, a presentation, and a manuscript for academic publication.
Skills, Techniques, Methods
- Computer vision
- Machine learning
- Geospatial data processing
Research Conditions
The research will be conducted primarily in person in the Multimodal Vision Research Laboratory (MVRL) in McKelvey Hall. It will involve software development, dataset curation, training machine learning models, and model performance analysis.
Team Structure and Opportunities
The undergraduate fellow will work closely with a Ph.D. student mentor from MVRL, with weekly meetings with Nathan Jacobs and meetings every few weeks with our ecology collaborator. The fellow will be exposed to other Computer Vision research taking place in the lab through a weekly journal club and work-in-progress meeting.
Requirements
- Python programming
- Machine learning
