Re-identification of individuals from images using spot constellations: a case study in Arctic charr (Salvelinus alpinus).
Re-identification of individuals from images using spot constellations: a case study in Arctic charr (Salvelinus alpinus).
复制标题
DOI：
10.1098/rsos.201768
复制
发表时间：
2021-07
影响因子：
3.5
通讯作者：
Terzić K
中科院分区：
文献类型：
--
作者：
De Bicki IT;Mittell EA;Kristjánsson BK;Leblanc CA;Morrissey MB;Terzić K
重新识别个体的能力是基于个体的研究的基础，这些研究需要估计野生种群中许多重要的生态和进化参数。传统的标记个体和跟踪个体的方法可能是侵入性的和不完善的，这可能会影响这些估计，并给种群管理带来不确定性。在这里，我们提出了一种摄影重新识别方法，使用图像中的斑点星座，通过时间来匹配标本。北极红点鲑（Salvelinus alpinus）的照片被用作案例研究。经典的计算机视觉技术与新的深度学习技术进行了比较，用于掩模和斑点提取。我们发现，在一小组人类注释的照片上训练的U-Net方法比基线特征工程方法表现得更好。为了匹配的斑点星座，两种算法进行了调整，并根据是否是一个完全或半自动化的设置是首选，我们展示了如何可以实现这些算法之一或组合。在我们的案例研究中，我们的管道不仅成功地从照片中识别出未标记的个体，还重新识别了丢失标签的个体，从而使我们对生存率的估计增加了约4%。总的来说，我们的多步骤管道几乎不需要人工监督，可以应用于许多生物体。
The ability to re-identify individuals is fundamental to the individual-based studies that are required to estimate many important ecological and evolutionary parameters in wild populations. Traditional methods of marking individuals and tracking them through time can be invasive and imperfect, which can affect these estimates and create uncertainties for population management. Here we present a photographic re-identification method that uses spot constellations in images to match specimens through time. Photographs of Arctic charr (Salvelinus alpinus) were used as a case study. Classical computer vision techniques were compared with new deep-learning techniques for masks and spot extraction. We found that a U-Net approach trained on a small set of human-annotated photographs performed substantially better than a baseline feature engineering approach. For matching the spot constellations, two algorithms were adapted, and, depending on whether a fully or semi-automated set-up is preferred, we show how either one or a combination of these algorithms can be implemented. Within our case study, our pipeline both successfully identified unmarked individuals from photographs alone and re-identified individuals that had lost tags, resulting in an approximately 4% increase in our estimate of survival rate. Overall, our multi-step pipeline involves little human supervision and could be applied to many organisms.
登录
查看更多内容
影响因子：
8
作者：
Ardovini, A.;Cinque, L.;Sangineto, E.
通讯作者：
Sangineto, E.
影响因子：
19.5
作者：
Hughes, Benjamin;Burghardt, Tilo
通讯作者：
Burghardt, Tilo
影响因子：
1.7
作者：
Hyslop, Natalie L.;Stevenson, Dirk J.;Oli, Madan K.
通讯作者：
Oli, Madan K.
影响因子：
5
作者：
Johnson, Heather E.;Mills, L. Scott;Wehausen, John D.
通讯作者：
Wehausen, John D.
影响因子：
2.4
作者：
Loos, Alexander;Ernst, Andreas
通讯作者：
Ernst, Andreas