Events

CILVR Seminar: From the Sun to Birds: Using Computer Vision to Measure The Universe

Speaker: David Fouhey

Location: 60 Fifth Avenue, Room 7th floor common area

Date: Thursday, February 1, 2024

It's exciting times as computer vision has started to change from a discipline with potential to one with impact. During this transition period, one opportunity I'm particularly excited about is collaborating with researchers in the sciences to help them obtain better data. Accordingly, I've been translating what I've learned from the past decade in 3D vision into the science domains, focusing on solar physics and evolutionary ecology. While studying objects of radically different sizes, both areas are unified by a desire to obtain better measurements more quickly, and in both, I've been able to build lasting long-term collaborations with experts.

In this talk, I'll show off the systems that I've built with members of my research group and collaborators. I'll focus primarily on solar physics, where we've developed a series of systems with a primary focus on obtaining better measurements of the Sun's vector magnetic field. These vector measurements of the solar magnetic field serve as cornerstones for scientific investigation of the Sun as well as important space weather monitoring efforts. I'll discuss how the field gets measured in practice and show our systems that combine capabilities of multiple instruments. Our systems produce maps of the magnetic field with higher fidelity, fewer artifacts, and far higher throughput. As a byproduct, our efforts have resolved long-standing calibration issues as well. Towards the end of the talk, I'll briefly discuss a project in evolutionary ecology, where we've built low-cost high-throughput systems to measure skeletal traits of bird specimens. These specimens largely sit in museums unmeasured due to high costs for manual or CT-scan measurement, but by measuring them quickly and cheaply, we can enable testing of old hypotheses at vast scales.

This line of work is joint work with many researchers, but my current student collaborators who these results are co-authored with are Ruoyu Wang and Richard Higgins.