Vulcan’s Machine Learning team partnered with Sealife Response + Rehabilitation + Research to develop the Aquatic Mammal Photogrammetry Tool.

The Aquatic Mammal Photogrammetry Tool (AMPT) uses machine learning to help researchers analyze large numbers of drone photos faster in order to provide health metrics for Southern Resident killer whales. It is the first machine learning tool of its kind to combine individual recognition with photogrammetry for killer whales.

Until now, processing aerial photogrammetry images has relied on manual analysis done by humans, which makes it labor-intensive, expensive and slow. 

Vulcan’s machine learning team partnered with SR3 to see if they could accelerate the process. AMPT uses machine learning and an end-user tool to dramatically decrease the time needed for image analysis, from around 6 months down to a matter of weeks, or even days.

Faster turnaround on health metric data will allow SR3 researchers provide health metrics to management groups, including identifying vulnerable whales and whales of concern, with an aim to help guide management decisions directed towards the recovery of Southern Resident killer whales.

On April 28, 2021, representatives from Vulcan and SR3 gathered for an online presentation and demonstration of the new tool. Highlights from the panel can be viewed below. For a recording of the full panel discussion, please email press@vulcan.com. 

Highlights from press briefing on the new Aquatic Mammal Photogrammetry Tool