Automated conservation with deep learning AI for camera-trap identification of species and individuals

The project will use deep learning AI approaches in conservation ecology for the automated identification of species and individuals from camera trap videos. First, using chimpanzee camera trap data, we will develop software to recognise the species within images using deep learning. The coding platform we will use is PyTorch, which has been previously used for such AI training for other species (Ramirez, 2022; Kholiavchenko, 2022; Lamba & Cassey, 2019; Wearn, Freeman & Jacoby, 2019). Second, we will develop software for the identification of individual chimpanzees, for example using facial recognition and gait recognition. Third, the development of software for the identification of symptoms of visual diseases, such as leprosy, will be attempted. To the best of our knowledge, this is a novel application for species in the wild and has not been attempted previously. This pioneering research has extremely strong links to real-world applications that extend further than the scope of this project. The addition of deep learning AI to identifications through camera-trap datasets not only promises to decrease the time of human-effort on such a task, it also facilitates the draining of a vast bottleneck in conservation research. Thus, harnessing the power of computer science to aid in the conservation of threatened species.