This early research was conducted between 2006-2009. The research aimed at exploring some first non-invasive identification solutions for problems in field biology and to better understand and help conserve endangered species. Specifically, we developed approaches to monitor individuals in uniquely patterned animal populations using techniques that originated in computer vision and human biometrics. Work was centred around the African penguin (Spheniscus demersus).
During the project we provided a proof of concept for an autonomously operating prototype system capable of monitoring and recognising a group of individual African penguins in their natural environment without tagging or otherwise disturbing the animals. The prototype system was limited to very good acquisitional and environmental conditions, and operated on animals with sufficiently complex natural patterns.
Research was conducted together with the Animal Demography Unit at the University of Cape Town, South Africa. The project was funded by the Leverhulme Trust, with long-term support in the field from the Earthwatch Institute, and with pilot tests run in collaboration with Bristol Zoo Gardens.
Whilst deep learning approaches of today have replaced most of the traditional identification techniques of the 2000s, the practical and applicational insights gained in this project helped inform some of our current work on animal biometrics.