New artificial intelligence software developed by researchers from Oxford University may change the way researchers and wildlife conservationists observe and research animals in the wild.
The team created the software which can now observe, track, recognize, and detect chimpanzees. The hope is that the software will be used to observe numerous types of animals in the wild.
Using video footage of 23 chimpanzees in Bossou in Guinea, West Africa, the team studied over 50 hours of archival tapes — that's 14 years' worth. This gave the team 10 million facial images to work with.
How did the team create the algorithm?
With video images taken from Kyoto University's Primate Research Institute (PRI), the research team was able to create and train the computer model to recognize individual chimpanzees' faces.
It's the first software of its kind to continuously track and recognize individual primates in several different poses and positions. Furthermore, the computer can recognize the chimpanzees even when lighting is poor, image quality is low, and when there are blurry movements.
"Access to this large video archive has allowed us to use cutting edge deep neural networks to train models at a scale that was previously not possible," said Arsha Nagrani, co-author of the study and DPhil student at the Department of Engineering Science, University of Oxford.
Nagrani continued, "Additionally, our method differs from previous primate face recognition software in that it can be applied to raw video footage with limited manual intervention or pre-processing, saving hours of time and resources."
What are the main uses for the software?
There are a number of useful uses for the new software, primarily keeping an eye on specific species for conservation purposes.
"For species like chimpanzees, which have complex social lives and live for many years, getting snapshots of their behaviour from short-term field research can only tell us so much," said Dan Schofield, researcher and DPhil student at Oxford University's Primate Models Lab, School of Anthropology.
New paper from a great collaboration: Chimpanzee face recognition through deep learning. Amazing effort by @Dan_schofield_ @NagraniArsha enabling automated processing of decades of wild chimp video data. https://t.co/9E0JKbqrWd Also w/ @primobevolab @Oxford_VGG @JpnMonkeyCentre pic.twitter.com/pmvUYusSkV— Dora Biro (@dora_biro_) September 4, 2019
Schofield continued, "By harnessing the power of machine learning to unlock large video archives, it makes it feasible to measure behaviour over the long term, for example observing how the social interactions of a group change over several generations."
Even though this research focused solely on chimpanzees, the software could be used for other species.
Nagrani pointed out that their software is available for those in the community to use.
"All our software is available open-source for the research community," said Nagrani. "We hope that this will help researchers across other parts of the world apply the same cutting-edge techniques to their unique animal data sets."
And Schofield ended by saying: "With an increasing biodiversity crisis and many of the world's ecosystems under threat, the ability to closely monitor different species and populations using automated systems will be crucial for conservation efforts, as well as animal behaviour research." A great cause which goes hand in hand with highlighting the many uses of AI.
The findings were published in Science Advances.