DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
复制标题
DOI：
10.7554/elife.47994
复制
发表时间：
2019-10-01
期刊：
影响因子：
7.7
通讯作者：
Couzin, Iain D.
中科院分区：
文献类型：
--
作者：
Graving, Jacob M.;Chae, Daniel;Couzin, Iain D.
定量行为测量对于回答从神经科学到生态学的跨学科问题非常重要。最先进的深度学习方法在数据质量和细节方面取得了重大进展，允许研究人员直接从图像或视频中自动估计动物身体部位的位置。然而，目前可用的动物姿态估计方法在速度和鲁棒性方面具有局限性。在这里，我们介绍了一个新的易于使用的软件工具包DeepPoseKit，它使用一个高效的多尺度深度学习模型（称为Stacked DenseNet）和一个快速的基于GPU的峰值检测算法来解决这些问题，该算法用于以亚像素精度估计关键点位置。与目前可用的方法相比，这些进步将处理速度提高了> 2倍，而不会损失准确性。我们证明了我们的方法的多功能性与多个具有挑战性的动物姿态估计任务，在实验室和现场设置，包括相互作用的个人群体。我们的工作减少了使用先进工具测量行为的障碍，并在行为科学中具有广泛的适用性。
Quantitative behavioral measurements are important for answering questions across scientific disciplines-from neuroscience to ecology. State-of-the-art deep-learning methods offer major advances in data quality and detail by allowing researchers to automatically estimate locations of an animal's body parts directly from images or videos. However, currently available animal pose estimation methods have limitations in speed and robustness. Here, we introduce a new easy-to-use software toolkit, DeepPoseKit, that addresses these problems using an efficient multi-scale deep-learning model, called Stacked DenseNet, and a fast GPU-based peak-detection algorithm for estimating keypoint locations with subpixel precision. These advances improve processing speed >2x with no loss in accuracy compared to currently available methods. We demonstrate the versatility of our methods with multiple challenging animal pose estimation tasks in laboratory and field settings-including groups of interacting individuals. Our work reduces barriers to using advanced tools for measuring behavior and has broad applicability across the behavioral sciences.