ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images
School of Science and Technology, University of New England, Armidale, NSW 2351, Australia
School of Environmental and Rural Science, University of New England, Armidale, NSW 2351, Australia
Vertebrate Pest Research Unit, NSW Department of Primary Industries, Allingham St, Armidale, NSW 2351, Australia
Vertebrate Pest Research Unit, NSW Department of Primary Industries, 1447 Forest Road, Orange, NSW 2800, Australia
Manaaki Whenua—Landcare Research, Private Bag 92170, Auckland 1142, New Zealand
IO Design Australia, Armidale, NSW 2350, Australia
Vertebrate Pest Research Unit, NSW Department of Primary Industries, PO Box 530, Coffs Harbour, NSW 2450, Australia
Author to whom correspondence should be addressed.
Received: 1 November 2019
Revised: 13 December 2019
Accepted: 20 December 2019
Published: 27 December 2019
Camera trap wildlife surveys can generate vast amounts of imagery. A key problem in the wildlife ecology field is that vast amounts of time is spent reviewing this imagery to identify the species detected. Valuable resources are wasted, and the scale of studies is limited by this review process. The use of computer software capable of extracting false positives, automatically identifying animals detected and sorting imagery could greatly increase efficiency. Artificial intelligence has been demonstrated as an effective option for automatically identifying species from camera trap imagery. Currently available code bases are inaccessible to the majority of users; requiring high-performance computers, advanced software engineering skills and, often, high-bandwidth internet connections to access cloud services. The ClassifyMe software tool is designed to address this gap and provides users the opportunity to utilise state-of-the-art image recognition algorithms without the need for specialised computer programming skills. ClassifyMe is especially designed for field researchers, allowing users to sweep through camera trap imagery using field computers instead of office-based workstations.