If reductions in habitats due to deforestation and climate change weren't enough, many species around the world are being driven to the brink of extinction from poaching. We've already seen numerous efforts employing drones to help combat this threat, and now the aerial technology has been paired with software and techniques used by astronomers in a system designed to automatically detect and monitor wildlife in hard to reach areas, even at night when most poaching occurs.
The new system is the result of a collaboration between astrophysicists and ecologists at Liverpool John Moores University (LJMU) and sees drone technology used by conservationists combined with thermal imaging technology and software used by astronomers. Building on machine-learning algorithms and astronomical detection tools developed through the open source Astropy Project, the system has been trained to recognize different types of animals in various landscapes and vegetation.
"With thermal infrared cameras, we can easily see animals as a result of their body heat, day or night, and even when they are camouflaged in their natural environment," explains says team member Dr Claire Burke. "Since animals and humans in thermal footage 'glow' in the same way as stars and galaxies in space, we have been able to combine the technical expertise of astronomers with the conservation knowledge of ecologists to develop a system to find the animals or poachers automatically."
An initial pilot project conducted in mid 2017 at a farm in the Wirral in northwest England tested the concept using infrared drone footage of humans and cows. The LJMU team then followed this by teaming up with Knowsley Safari and Chester Zoo to capture the unique thermal profiles of various animals, including rhinos and baboons, and build up a library of different animal thermal signatures. The team has now moved onto field tests to detect endangered animals in their native habitats.
"We held our first field trial in South Africa last September to detect Riverine rabbits, one of the most endangered species of mammal in the world," says Burke. "The rabbits are very small, so we flew the drone quite low to the ground at a height of 20 meters (66 ft). Although this limited the area we could cover with the drone, we managed five sightings. Given that there have only been about 1,000 sightings of Riverine rabbits by anyone in total, it was a real success."
Having already developed software that takes into account the effects of vegetation blocking body heat to allow animals to be detected behind trees or leaves, the team is now looking to upgrade it so that it can compensate for environmental factors, including weather and atmospheric effects.
"Humidity can be an issue, but our biggest problems occur when the temperature of the ground is very similar to that of the animal we are trying to detect," says Maisie Rashman.
For the rest of the article, see here