Making top-down human pose estimation method present both good performance
and high efficiency is appealing. mask rcnn can largely improve the efficiency
by conducting person detection and pose estimation in a si
通过提出的 HG-RCNN 网络,借助 Mask-RCNN 和 Hourglass 结构进行多人 3D 人体姿态估计,实现对每个感兴趣区域(RoI)中 2D 关键点的先预测后提升,最终采用弱透视投影模型和焦距和根偏移的联合优化将估计的 3D 姿态置于相机坐标系下,该网络简单模块化且无需多人 3D 姿态数据集,取得了 MuPoTS-3D 数据集的最优性能,并能近似在相机坐标系下估计 3D 姿态。