身体姿势估计 - Human Pose Estimation

1. 简介

   人体姿势估计主要采用：数据驱动、从下到上的方法；在此方法中，像素被独立地标记为身体的某一部分，或投票决定关节的位置。

2. 2D身体姿势估计

    【1】(2016) Sparseness Meets Deepness: 3D Human Pose Estimation From Monocular Video. 
              Xiaowei Zhou, Menglong Zhu, Spyridon Leonardos, Konstantinos G. Derpanis, Kostas Daniilidis   

    【2】(2016)    End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation. 

             Wei Yang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang

    【3】(2014) DeepPose: Human Pose Estimation via Deep Neural Networks
            Alexander Toshev, Christian Szegedy (Google)

3. 3D身体姿势估计

    【1】(2016) Rolling Rotations for Recognizing Human Actions From 3D Skeletal Data. 
             Raviteja Vemulapalli, Rama Chellapa