Researchers based in the greater Yellowstone National Park area have found a new way to identify mountain lions-also referred as pumas- by using facial recognition. And it is proving to be effective to monitor these creatures that are highly elusive. "Mountain lions are really hard to directly observe." said Peter Alexander, a research biologist leading the research project.
One tool they once used is a camera trap, which is attached to something along the animal's regular path. When motion is detected, the trap gets a shot of the mountain lion as it passes by. The cameras even have an infra-red (红外线的)flash for nighttime photos without disturbing the animal.
Researchers around the world use this type of tool to estimate population numbers of species. But according to Alexander, there's a problem with this method when it comes to ID'ing mountain lions.
All mountain lion around the world have light, sandy colored fur down their sides. The scientific name for a mountain lion, Puma concolor, literally translates to "one color". This lack of unique coloration (自然花纹)on the their body sides means researchers like Alexander can't usually tell if one puma crosses a camera trap five times, or if five individual animals pass by.
However, it's a different story with their distinctive facial markings. Alexander and his team added some devices to their camera traps so that when motion was detected, a puma kitten call was played. This noise reliably attracted passerby pumas so that they looked up long enough for the camera trap to grab a shot for facial recognition.
Compared to the traditional side angle camera trap, the new attention-getting device was about 92% more accurate. This work was recently published in the journal Ecology and Evolution.
This study is an important step to being able to more confidently identify and track animals. Getting head images of mountain lions also opens up new opportunities to involve AI techniques. Alexander says that this new camera trap method could be used for tracking other wild animals that lack distinguishing side colors but have unique features elsewhere.