Pandas aren t all black and white Some come in a different shade, and scientists now understand why - LocalNews8 com localnews8.com - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from localnews8.com Daily Mail and Mail on Sunday newspapers.
In their research, associate professor from the NRS Department Tiejun Wang and his master's student Zijing Wu developed an AI-model to automatically locate and count large herds of migratory ungulates (wildebeest and zebra). They used their method in the Serengeti-Mara ecosystem using fine-resolution (38–50 cm) satellite imagery.
Counting elephants from space? That’s the aim of the project. To do so, earth-observation satellites and a branch of artificial intelligence (AI) known as machine learning are being deployed.
How so? Researchers are using the highest resolution satellite images currently available, which are processed and analysed automatically by a computer algorithm that has been trained with more than 1,000 images of elephants to help spot elephants in the wild. The AI involvement means the creatures can be counted even in hard-to-spot areas covered with trees or shrubs.
It’s an international project? A team from the University of Oxford, in collaboration with Dr Olga Isupova of the University of Bath and Dr. Tiejun Wang, of the University of Twente, are leading the effort, saying the work is “vital” to ensure the survival of the species.
Ideas, Inventions And Innovations
Elephants Counted from Space with Algorithms and Satellite Cameras
For the first time, scientists have successfully used satellite cameras coupled with deep learning to count animals in complex geographical landscapes, taking conservationists an important step forward in monitoring populations of endangered species. Elephants in woodland as seen from space. Green rectangles show elephants detected by the algorithm, red rectangles show elephants verified by humans.
Credit: University of Bath
For this research, the satellite Worldview 3 used high-resolution imagery to capture African elephants moving through forests and grasslands. The automated system detected animals with the same accuracy as humans are able to achieve.