1. A typical camera trap survey may produce millions of images that require slow, expensive manual review. Consequently, critical conservation questions may be answered too slowly to support decision‐making. Recent studies demonstrated the potential for computer vision to dramatically increase efficiency in image‐based biodiversity surveys; however, the literature has focused on projects with a large set of labelled training images, and hence many projects with a smaller set of labelled images cannot benefit from existing machine learning techniques. Furthermore, even sizable projects have struggled to adopt computer vision methods because classification models overfit to specific image backgrounds (i.e. camera locations).
2. In this paper, we combine the power of machine intelligence and human intelligence via a novel active learning system to minimize the manual work required to train a computer vision model. Furthermore, we utilize object detection models and transfer learning to prevent overfitting to camera locations. To our knowledge, this is the first work to apply an active learning approach to camera trap images.
3. Our proposed scheme can match state‐of‐the‐art accuracy on a 3.2 million image dataset with as few as 14,100 manual labels, which means decreasing manual labelling effort by over 99.5%. Our trained models are also less dependent on background pixels, since they operate only on cropped regions around animals.
4. The proposed active deep learning scheme can significantly reduce the manual labour required to extract information from camera trap images. Automation of information extraction will not only benefit existing camera trap projects, but can also catalyse the deployment of larger camera trap arrays.

中文翻译：

---

用于相机陷阱图像中物种识别和计数的深度主动学习系统

1. 典型的相机陷阱调查可能会产生数百万张需要缓慢，昂贵的手动检查的图像。因此，关键的保护问题可能回答得太慢而无法支持决策。最近的研究表明，计算机视觉可以极大地提高基于图像的生物多样性调查的效率。但是，文献集中于带有大量标记训练图像的项目，因此许多带有较小标记图像的项目无法从现有的机器学习技术中受益。此外，由于分类模型过分适合特定的图像背景（即相机位置），因此即使是规模较大的项目也难以采用计算机视觉方法。
2. 在本文中，我们通过新颖的主动学习系统将机器智能和人类智能的功能结合在一起，以最大程度地减少训练计算机视觉模型所需的人工工作。此外，我们利用物体检测模型和转移学习来防止过度拟合相机位置。就我们所知，这是将主动学习方法应用于相机陷阱图像的第一项工作。
3. 我们提出的方案可以在多达320万张图像数据集上达到最先进的精度，而手工标签的数量却只有14,100张，这意味着人工标签工作量减少了99.5％以上。我们训练有素的模型还较少依赖于背景像素，因为它们仅在动物周围的裁剪区域上起作用。
4. 拟议的主动深度学习方案可以显着减少从相机陷阱图像中提取信息所需的体力劳动。信息提取的自动化不仅将使现有的相机陷阱项目受益，而且还将促进更大的相机陷阱阵列的部署。