RT Journal Article
SR Electronic
T1 Improving the accessibility and transferability of machine learning algorithms for identification of animals in camera trap images: MLWIC2
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.03.18.997700
DO 10.1101/2020.03.18.997700
A1 Michael A. Tabak
A1 Mohammad S. Norouzzadeh
A1 David W. Wolfson
A1 Erica J. Newton
A1 Raoul K. Boughton
A1 Jacob S. Ivan
A1 Eric A. Odell
A1 Eric S. Newkirk
A1 Reesa Y. Conrey
A1 Jennifer L. Stenglein
A1 Fabiola Iannarilli
A1 John Erb
A1 Ryan K. Brook
A1 Amy J. Davis
A1 Jesse S. Lewis
A1 Daniel P. Walsh
A1 James C. Beasley
A1 Kurt C. VerCauteren
A1 Jeff Clune
A1 Ryan S. Miller
YR 2020
UL http://biorxiv.org/content/early/2020/03/22/2020.03.18.997700.abstract
AB Motion-activated wildlife cameras (or “camera traps”) are frequently used to remotely and non-invasively observe animals. The vast number of images collected from camera trap projects have prompted some biologists to employ machine learning algorithms to automatically recognize species in these images, or at least filter-out images that do not contain animals. These approaches are often limited by model transferability, as a model trained to recognize species from one location might not work as well for the same species in different locations. Furthermore, these methods often require advanced computational skills, making them inaccessible to many biologists.We used 3 million camera trap images from 18 studies in 10 states across the United States of America to train two deep neural networks, one that recognizes 58 species, the “species model,” and one that determines if an image is empty or if it contains an animal, the “empty-animal model.”Our species model and empty-animal model had accuracies of 96.8% and 97.3%, respectively. Furthermore, the models performed well on some out-of-sample datasets, as the species model had 91% accuracy on species from Canada (accuracy range 36-91% across all out-of-sample datasets) and the empty-animal model achieved an accuracy of 91-94% on out-of-sample datasets from different continents.Our software addresses some of the limitations of using machine learning to classify images from camera traps. By including many species from several locations, our species model is potentially applicable to many camera trap studies in North America. We also found that our empty-animal model can facilitate removal of images without animals globally. We provide the trained models in an R package (mlwic2: Machine Learning for Wildlife Image Classification in R), which contains Shiny Applications that allow scientists with minimal programming experience to use trained models and train new models in six neural network architectures with varying depths.