Deep learning-based methods for individual recognition in small birds

Cite This

Files in this item

Checksum: MD5:8a5bde26b9a9261abf8ad36739fa88da

FERREIRA, André C., Liliana R. SILVA, Francesco RENNA, Hanja B. BRANDL, Julien P. RENOULT, Damien R. FARINE, Rita COVAS, Claire DOUTRELANT, 2020. Deep learning-based methods for individual recognition in small birds. In: Methods in Ecology and Evolution. British Ecological Society. ISSN 2041-2096. eISSN 2041-210X

@article{Ferreira2020learn-50104, title={Deep learning-based methods for individual recognition in small birds}, year={2020}, issn={2041-2096}, journal={Methods in Ecology and Evolution}, author={Ferreira, André C. and Silva, Liliana R. and Renna, Francesco and Brandl, Hanja B. and Renoult, Julien P. and Farine, Damien R. and Covas, Rita and Doutrelant, Claire} }

Farine, Damien R. 1. Individual identification is a crucial step to answer many questions in evolutionary biology and is mostly performed by marking animals with tags. Such methods are well established, but often make data collection and analyses time consuming, or limit the contexts in which data can be collected.<br /><br />2. Recent computational advances, specifically deep learning, can help overcome the limitations of collecting large-scale data across contexts. However, one of the bottlenecks preventing the application of deep learning for individual identification is the need to collect and identify hundreds to thousands of individually-labelled pictures from which to train convolutional neural networks (CNNs).<br /><br />3. Here, we describe procedures for automating the collection of training data, generating training datasets, and training CNNs to allow individual identification of individual birds. We apply our procedures to three small bird species, the sociable weaver Philetairus socius, the great tit Parus major and the zebra finch Taeniopygia guttata, representing both wild and captive contexts.<br /><br />4. We first show how the collection of individually labelled images can be automated, allowing the construction of training datasets consisting of hundreds of images per individual. Second, we describe how to train a CNN to uniquely re-identify each individual in new images. Third, we illustrate the general applicability of CNNs for studies in animal biology by showing that trained CNNs can re-identify individual birds in images collected in contexts that differ from the ones originally used to train the CNNs. Finally, we present a potential solution to solve the issues of new incoming individuals.<br /><br />5. Overall, our work demonstrates the feasibility of applying state-of-the-art deep learning tools for individual re-identification of birds, both in the lab and in the wild. These techniques are made possible by our approaches that allow efficient collection of training data. The ability to conduct individual recognition of birds without requiring external markers that can be visually identified by human observers represents a major advance over current methods. Renoult, Julien P. Brandl, Hanja B. 2020-07-02T12:08:05Z eng Silva, Liliana R. 2020-07-02T12:08:05Z Deep learning-based methods for individual recognition in small birds Ferreira, André C. Brandl, Hanja B. Doutrelant, Claire Silva, Liliana R. Renoult, Julien P. Ferreira, André C. Covas, Rita Covas, Rita Farine, Damien R. Renna, Francesco 2020 Renna, Francesco terms-of-use Doutrelant, Claire

Downloads since Jul 2, 2020 (Information about access statistics)

Ferreira_2-1fpdk03l25c7i7.pdf 84

This item appears in the following Collection(s)

Search KOPS


My Account