Listed as extremely endangered by the International Union for Conservation of Nature, with less than 4,000 individuals left in the wild, the species could be actually saved from extinction with Artificial Intelligence(AI)
The snow leopard is a large cat native to the mountain ranges of Central and South Asia. Living in those remote region and being extremely elusive, make these gorgeous felines impossible to study. However, in their attempt to conserve the species, the Snow Leopard Trust group used traps cameras to capture more than one million images.
“Suddenly, I hear a chuff and a snow leopard walks right in front of me. He looked at me with big round eyes, almost as if saying, ‘How did you get so close to me without me knowing it?’ They’re almost overconfident about their invisibility. Then he turned around and fled away like a ribbon,” Koustubh Sharma a senior regional ecologist at the Snow Leopard Trust.
However, those traps cameras are using heat and motion sensor. Therefore, they capture photos of other wild animals too, and not only the elusive leopards. So imagine how long it might take to manually sort hundred of thousands of images?
So here’s where the AI steps in. A new Microsoft AI solution is helping the researcher team to save a lot of time, by accelerating this process. According to Microsoft News, the algorithm is identifying the snow leopard images and it’s able to sort hundreds of thousands of photos in only a few minutes.
“When you’re camera-trapping in an area, you’re basically giving snow leopards an opportunity to take their selfies,” Sharma said. “You need to know where they are and how many they are to conserve them. But sometimes you end up with thousands of pictures that are not relevant. That’s where AI comes to the rescue.”
The developing engineers are hoping the technology will soon be able to identify a specific individual out of these photos. “The question is, ‘Is the snow leopard in Picture 1,240 the same snow leopard in Picture 1,000,240?'”
“How do you tie these pictures together? Right now, the process is labor-intensive and error-prone, and as you get more images, it’s like adding more pieces to a 40,000-piece jigsaw puzzle. We hope deep learning can help us find likely matches,” said Mark Hamilton, the Microsoft software engineer who created the model.
The informations about the species are vital in the scientists efforts to save the snow leopard. Therefore they need as much photos as possible. “More research is needed,” Sharma says. “AI can help us speed up the task of estimating the world’s snow leopard populations.”