Deep learning-based methods for individual recognition in small birds
Deep learning-based methods for individual recognition in small birds
复制标题
DOI：
10.1111/2041-210x.13436
复制
发表时间：
2020-07-26
影响因子：
6.6
通讯作者：
Doutrelant, Claire
中科院分区：
文献类型：
--
作者：
Ferreira, Andre C.;Silva, Liliana R.;Doutrelant, Claire
个体识别是回答进化生物学中许多问题的关键一步，主要是通过给动物贴上标签来完成的。这些方法是行之有效的，但往往使数据收集和分析耗时，或者限制了可以收集数据的上下文。最近的计算进步，特别是深度学习，可以帮助克服跨环境收集大规模数据的局限性。然而，阻碍深度学习用于个体识别的瓶颈之一是需要收集和识别数百到数千张单独标记的图片来训练卷积神经网络（cnn）。在这里，我们描述了自动收集训练数据、生成训练数据集和训练cnn以识别单个鸟类的过程。我们将我们的程序应用于三种小型鸟类，即群居编织鸟philetairus socius，大鸟parus major和斑马雀taeniopygia guttata，分别代表野生和圈养环境。我们首先展示了如何自动收集单独标记的图像，允许构建由每个人数百张图像组成的训练数据集。其次，我们描述了如何训练CNN来唯一地重新识别新图像中的每个个体。第三，我们通过显示训练后的cnn可以重新识别在不同于最初用于训练cnn的环境中收集的图像中的单个鸟类，来说明cnn在动物生物学研究中的普遍适用性。最后，我们提出了一个潜在的解决方案，以解决新入职人员的问题。总的来说，我们的工作证明了在实验室和野外应用最先进的深度学习工具进行鸟类个体识别的可行性。我们的方法允许有效地收集训练数据，从而使这些技术成为可能。在不需要外部标记的情况下对鸟类进行个体识别的能力，可以由人类观察者进行视觉识别，这是目前方法的一大进步。
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. 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 to train convolutional neural networks (CNNs). Here we describe procedures for automating the collection of training data, generating training datasets, and training CNNs to allow identification of individual birds. We apply our procedures to three small bird species, the sociable weaverPhiletairus socius,the great titParus majorand the zebra finchTaeniopygia guttata, representing both wild and captive contexts. 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. Overall, our work demonstrates the feasibility of applying state-of-the-art deep learning tools for individual identification of birds, both in the laboratory 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.