Deep learning tools for the measurement of animal behavior in neuroscience
Deep learning tools for the measurement of animal behavior in neuroscience
复制标题
DOI：
10.1016/j.conb.2019.10.008
复制
发表时间：
2020-02-01
影响因子：
5.7
通讯作者：
Mathis, Alexander
中科院分区：
文献类型：
--
作者：
Mathis, Mackenzie Weygandt;Mathis, Alexander
计算机视觉的最新进展使准确、快速和稳健的动物行为测量成为现实。在过去的几年里，专门为帮助测量行为而设计的强大工具已经取得了成果。在这里，我们讨论捕捉动物姿势（姿势估计）如何通过新的深度学习方法快速发展。尽管挑战仍然存在，但我们预计新深度学习工具的快速发展将迅速改变可实现的现实世界神经科学的格局。
Recent advances in computer vision have made accurate, fast and robust measurement of animal behavior a reality. In the past years powerful tools specifically designed to aid the measurement of behavior have come to fruition. Here we discuss how capturing the postures of animals - pose estimation - has been rapidly advancing with new deep learning methods. While challenges still remain, we envision that the fast-paced development of new deep learning tools will rapidly change the landscape of realizable real-world neuroscience.