Skip to main content
Loading Events

« All Events

Ryan Farrell - Computer Vision for Wildlife Monitoring and Conservation

September 29 @ 10:30 am MDT

Ryan Farrell
Associate Professor
Brigham Young University

farrell@cs.byu.edu

Computer Vision for Wildlife Monitoring and Conservation

Join Via Zoom

Biography

Ryan Farrell is an Associate Professor and Associate Chair in the Computer Science Department at Brigham Young University in Provo, Utah. His research interests are primarily focused on the challenges inherent in object recognition, particularly work on problems such as fine-grained recognition, animal biometrics and pose-estimation. He received an NSF CAREER Award in 2017 to investigate generalized pose-normalization for large-scale fine-grained recognition. He routinely serves on program committees and as an area chair for top vision conferences such as CVPR, ICCV and ECCV. He served as program chair from 2019-2022 and is currently serving as chair for WACV 2023.
In addition to his research in computer vision, he has interests in Computer Science Education and also has a keen interest in algorithms and data structures for problem solving. He coaches BYU’s competitive programming team, which just this last May, placed 26th at the North American Championships of the ICPC (International Collegiate Programming Contest).

Abstract

In the last 10 years, the field of deep learning has transformed computer vision, resulting in rapid advances in the Transportation (self-driving cars), Health Care (automatic diagnosis in medical imaging), and Retail (fully automated checkout, virtual dressing rooms, etc) sectors, among others. While the lion’s share of industrial research efforts have been directed towards these human-centric applications, important scientific fields such as field biology have received relatively little attention. In this talk, I will present ongoing work that my research team is pursuing, leveraging computer vision for wildlife monitoring and conservation. I will describe our work combining modern deep learning with classical vision and geometric methods to tackle such problems as fine-grained bird and insect recognition, animal biometrics for patterned animals, and population monitoring/new species discovery.