(CN) – A new detection system aims to protect endangered species from poachers by incorporating software and techniques designed to detect and study stars and galaxies.
Presented Tuesday at the European Week of Astronomy and Space Sciences (EWASS) in Liverpool, Britain, the project allows ecologists to monitor hard-to-reach areas – even at night, when most poaching occurs – through the use of drones that capture thermal infrared imagery. Astrophysical software and techniques are then applied to the imagery.
“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,” said Claire Burke, who will present the project at EWASS.
“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.”
The project incorporates machine-learning algorithms and astronomical detection tools developed through the open-source software Astropy. After an initial pilot phase to test the concept with infrared footage of cows and humans recorded by drone at a farm in the Wirral, the team worked with Chester Zoo and Knowsley Safari to compile libraries of imagery to fine-tune the software’s ability to recognize different types of animals in various types of vegetation and landscapes.
They are now embarking on field tests with endangered species.
“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. The rabbits are very small, so we flew the drone quite low to the ground at a height of 65.6 feet,” Burke said. “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.”
The team has developed software that models the effects of vegetation blocking body heat, enabling the detection of animals obscured by trees or leaves. The system is now being refined and upgraded to compensate for weather, atmospheric effects and other environmental factors. The technical components of the project will be presented EWASS by Maisie Rashman on Wednesday.
“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,” said Rashman, a researcher at Liverpool John Moores University.
The team will face their next field challenges in May as they look for spider monkeys in Mexico and orangutans in Malaysia, followed by a search for river dolphins in Brazil in June.
“Our aim is to make a system that is easy for conservationists and game wardens to use anywhere in the world, which will allow endangered animals to be tracked, found and monitored easily and poaching to be stopped before it happens,” said Burke.