Center for Neuroprosthetics, Center for Intelligent Systems, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland; Brain Mind Institute, School of Life Sciences, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland; The Rowland Institute at Harvard, Harvard University, Cambridge, MA, USA.
The Rowland Institute at Harvard, Harvard University, Cambridge, MA, USA; University of Tübingen and International Max Planck Research School for Intelligent Systems, Tübingen, Germany.
Neuron. 2020 Oct 14;108(1):44-65. doi: 10.1016/j.neuron.2020.09.017.
Extracting behavioral measurements non-invasively from video is stymied by the fact that it is a hard computational problem. Recent advances in deep learning have tremendously advanced our ability to predict posture directly from videos, which has quickly impacted neuroscience and biology more broadly. In this primer, we review the budding field of motion capture with deep learning. In particular, we will discuss the principles of those novel algorithms, highlight their potential as well as pitfalls for experimentalists, and provide a glimpse into the future.
从视频中无创地提取行为测量值受到一个事实的阻碍，即这是一个困难的计算问题。深度学习的最新进展极大地提高了我们直接从视频预测姿势的能力，这迅速广泛地影响了神经科学和生物学。在这个简介中，我们回顾了深度学习的新兴运动捕捉领域。特别是，我们将讨论这些新算法的原理，强调它们对实验者的潜在优势和陷阱，并展望未来。
