小柯机器人

2021年8月5日出版的《自然—方法学》杂志发表了瑞士洛桑联邦理工学院Pavan Ramdya等研究人员的合作成果。该研究开发出了LiftPose3D，一种基于深度学习的方法，用于将实验动物的二维姿势转化为三维姿势。

据研究人员介绍，无标记的三维（3D）姿势估计已经成为实验室动物运动学研究中不可或缺的工具。目前大多数方法是通过对基于深度网络的二维（2D）姿势估计进行多视角三角测量来恢复3D姿势。然而，三角测量需要多个同步相机和复杂的校准协议，这阻碍了其在实验室研究中的广泛采用。

Title: LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals

Author: Gosztolai, Adam, Gnel, Semih, Lobato-Ros, Victor, Pietro Abrate, Marco, Morales, Daniel, Rhodin, Helge, Fua, Pascal, Ramdya, Pavan

Issue&Volume: 2021-08-05

Abstract: Markerless three-dimensional (3D) pose estimation has become an indispensable tool for kinematic studies of laboratory animals. Most current methods recover 3D poses by multi-view triangulation of deep network-based two-dimensional (2D) pose estimates. However, triangulation requires multiple synchronized cameras and elaborate calibration protocols that hinder its widespread adoption in laboratory studies. Here we describe LiftPose3D, a deep network-based method that overcomes these barriers by reconstructing 3D poses from a single 2D camera view. We illustrate LiftPose3D’s versatility by applying it to multiple experimental systems using flies, mice, rats and macaques, and in circumstances where 3D triangulation is impractical or impossible. Our framework achieves accurate lifting for stereotypical and nonstereotypical behaviors from different camera angles. Thus, LiftPose3D permits high-quality 3D pose estimation in the absence of complex camera arrays and tedious calibration procedures and despite occluded body parts in freely behaving animals.

DOI: 10.1038/s41592-021-01226-z

Source: https://www.nature.com/articles/s41592-021-01226-z

Nature Methods：《自然—方法学》，创刊于2004年。隶属于施普林格·自然出版集团，最新IF：47.99
官方网址：https://www.nature.com/nmeth/
投稿链接：https://mts-nmeth.nature.com/cgi-bin/main.plex