High performance machine learning models can fully automate labeling of camera trap images for ecological analyses
High performance machine learning models can fully automate labeling of camera trap images for ecological analyses
复制标题
高性能机器学习模型可以完全自动标记相机陷阱图像以进行生态分析
DOI：
10.1101/2020.09.12.294538
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Whytock R
中科院分区：
文献类型：
--
作者：
Whytock R
越来越多地使用数字传感器阵列在广阔的地理区域收集生态数据。相机陷阱阵列已经成为调查许多陆地哺乳动物和鸟类的“黄金标准”方法，但这些阵列通常会生成数百万张图像，这些图像的处理具有挑战性。这导致数据收集和后续推理之间的延迟，这可能会在生态危机时期阻碍保护。为了解决这个问题，已经开发了机器学习算法来提高数据处理速度，但这些模型被认为不足以实现完全自动化的标记。在这里，我们提出了一种新的方法来构建和测试一个高性能的机器学习模型，用于全自动标记相机陷阱图像。作为案例研究，该模型对26种中非森林哺乳动物和鸟类物种（或类群）进行了分类。该模型是在相对较小的数据集（约30万张图像）上训练的，但可以推广到完全独立的数据，并在几个方面优于人类（例如检测“不可见”的动物）。我们展示了如何在生态建模的背景下，通过比较来自机器学习标签的物种丰富度，活动模式和占用率与来自专家标签的相同估计来评估模型的精度和准确性。结果表明，完全自动化的标签可以等同于专家标签时，计算这些广泛使用的生态指标。我们为用户社区提供了一个多平台的用户界面，用于离线运行模型，并得出结论，高性能的机器学习模型可以完全自动标记相机陷阱数据。生态传感器，如相机陷阱，部署在大的空间和时间尺度，以监测物种和社区。相机陷阱数据通常是巨大的（数百万张图像），手动处理时间会导致数据收集和生态推断之间的显着延迟。现有的机器学习模型可以减少处理时间，但很少用于生态分析的全自动工作流程，主要是因为用户对模型的精度和准确性缺乏信心。在这里，我们展示了一种新的、高性能的机器学习模型，它可以用来进行生态推理，相当于使用手动生成的专家标签。这些结果为使用相机陷阱阵列进行大规模、全自动生物多样性监测和预测铺平了道路。
Ecological data are increasingly collected over vast geographic areas using arrays of digital sensors. Camera trap arrays have become the ‘gold standard’ method for surveying many terrestrial mammals and birds, but these arrays often generate millions of images that are challenging to process. This causes significant latency between data collection and subsequent inference, which can impede conservation at a time of ecological crisis. To address this, machine learning algorithms have been developed to improve data processing speeds, but these models are not considered accurate enough for fully automated labeling. Here, we present a new approach to building and testing a high performance machine learning model for fully automated labeling of camera trap images. As a case-study, the model classifies 26 Central African forest mammal and bird species (or groups). The model was trained on a relatively small dataset (c.300,000 images) but generalizes to fully independent data and outperforms humans in several respects (e.g. detecting ‘invisible’ animals). We show how the model’s precision and accuracy can be evaluated in an ecological modeling context by comparing species richness, activity patterns and occupancy derived from machine learning labels with the same estimates derived from expert labels. Results show that fully automated labels can be equivalent to expert labels when calculating these widely-used ecological metrics. We provide the user-community with a multi-platform user interface for running the model offline, and conclude that high performance machine learning models can fully automate labeling of camera trap data.Significance statementLarge-scale ecological monitoring can be used to detect ecosystem change. Ecological sensors such as camera traps are deployed across large spatial and temporal scales to monitor species and communities. Camera trap data are often vast (millions of images) and manual processing times cause significant latency between data collection and ecological inference. Existing machine learning models can reduce processing times but are rarely used in fully automated workflows for ecological analyses, mainly because users lack confidence in the model’s precision and accuracy. Here, we show a new, high performance machine learning model can be used to make ecological inference that is equivalent to using manually generated, expert labels. These results pave the way for large-scale, fully automated biodiversity monitoring and forecasting using camera trap arrays.
登录
查看更多内容
影响因子：
5.5
作者：
O'Brien, Timothy G.;Ahumada, Jorge;Strindberg, Samantha
通讯作者：
Strindberg, Samantha
影响因子：
5.7
作者：
Bessone, Mattia;Kuehl, Hjalmar S.;Fruth, Barbara
通讯作者：
Fruth, Barbara
影响因子：
10.1
作者：
Farley, Scott S.;Dawson, Andria;Williams, John W.
通讯作者：
Williams, John W.
广义站点占用模型允许误报和漏报错误。
影响因子：
4.8
作者：
J. Andrew Royle;W. Link
通讯作者：
W. Link
在新相机陷阱项目中实现物种 ID 自动化的高效流程
DOI：
10.3897/biss.3.37222
发表时间：
2019
期刊：
Biodiversity Information Science and Standards
影响因子：
--
作者：
Sara Beery;Dan Morris;Siyu Yang;Marcel Simon;Arash Norouzzadeh;Neel Joshi
通讯作者：
Neel Joshi