Computers are playing spot the difference in the Serengeti. An image-recognition algorithm that can identify different species could make it easier to track animals in the wild.
Using a database of 3.2 million photos taken by hidden camera traps in the Serengeti National Park in Tanzania, Jeff Clune at the University of Wyoming in Laramie and his colleagues trained the deep-learning system to distinguish between 48 animal species, such as elephants, giraffes and gazelles. In tests, it correctly identified the species present in an image 92 per cent of the time.
Camera traps automatically take pictures of passing animals when triggered by heat and motion. This produces thousands or millions of photographs for ecologists to study, but people usually have to go through and label what each picture shows by hand, says Ali Swanson, who worked on the project while at the University of Oxford. If an algorithm could categorise at least …