论文标题
野生动植物摄像机捕获的自动距离估计
Automated Distance Estimation for Wildlife Camera Trapping
论文作者
论文摘要
持续的生物多样性危机要求对动物密度和丰度进行准确的估计，以确定生物多样性下降和保护干预措施的有效性的来源。相机陷阱与大量估计方法通常用于此目的。传统上，相机和观察到的动物之间的必要距离是在费力，完全手动或半自动过程中得出的。两种方法都需要参考图像材料，这既难以获取，也不适用于现有数据集。我们提出了一种全自动方法，我们称为自动距离估计（审核），以估算摄像头到动物的距离。我们利用现有的最新相对单眼深度估计，并将其与新的对齐程序结合使用，以估计度量距离。审核是完全自动化的，不需要将摄像机陷阱图像中的观测值与参考图像进行比较，也不需要捕获参考图像材料的捕获。因此，审计使生物学家和生态学家免除了大量工作量。我们在训练期间看不见动物园情景数据集的审计，在该数据集中，我们在仅0.9864米的所有动物实例上达到了平均绝对距离估计误差，平均相对误差（RER）为0.113。代码和使用说明可在https://github.com/pj-cs/distanceestimatimatimatracking上找到
The ongoing biodiversity crisis calls for accurate estimation of animal density and abundance to identify sources of biodiversity decline and effectiveness of conservation interventions. Camera traps together with abundance estimation methods are often employed for this purpose. The necessary distances between camera and observed animals are traditionally derived in a laborious, fully manual or semi-automatic process. Both approaches require reference image material, which is both difficult to acquire and not available for existing datasets. We propose a fully automatic approach we call AUtomated DIstance esTimation (AUDIT) to estimate camera-to-animal distances. We leverage existing state-of-the-art relative monocular depth estimation and combine it with a novel alignment procedure to estimate metric distances. AUDIT is fully automated and requires neither the comparison of observations in camera trap imagery with reference images nor capturing of reference image material at all. AUDIT therefore relieves biologists and ecologists from a significant workload. We evaluate AUDIT on a zoo scenario dataset unseen during training where we achieve a mean absolute distance estimation error over all animal instances of only 0.9864 meters and mean relative error (REL) of 0.113. The code and usage instructions are available at https://github.com/PJ-cs/DistanceEstimationTracking
