Computer vision challenges in wildlife conservation

Feb. 28, 2019 from 4:30 to 5:20 p.m. — Bagley Hall, room 154

Dan Morris, Principal Researcher, Microsoft AI for Earth


This talk is an overview of several problems in wildlife conservation where computer vision is poised to make a significant impact. We will survey four very different problems, and for each, we will discuss (1) why this problem is challenging from a computer vision perspective, (2) why solving this problem can support conservation, and (3) the data sets that the AI for Earth program at Microsoft is working with and the models we’re building to address this problem. And of course, (4) how you can get involved!


I’m a Principal Researcher in the Microsoft AI for Earth program, where I work primarily on computer vision applications in wildlife conservation, for example our Species Classification API. For five-ish years, I was in Microsoft’s Medical Devices Group, where I worked on signal processing and machine learning for cardiovascular health monitoring. Before that, I worked on signal processing and machine learning for input systemsmaking medical information more useful to hospital patients, automatic exercise analysis from wearable sensors, and generating musical accompaniment for vocal melodies (the “Songsmith” project). Before Microsoft, I studied neuroscience at Brown, and I developed brain-computer interfaces for research and clinical environments. My PhD work at Stanford focused on haptics and physical simulation for virtual surgery.