3-D Human Pose Estimation Using Cascade of Multiple Neural Networks

• Published in: IEEE transactions on industrial informatics 2019-04, Vol.15 (4), p.2064-2072
• Main Authors: Hoang, Van-Thanh, Jo, Kang-Hyun
• Format: Article
• Language: English
• Subjects: 3-D human pose estimation; Cameras; Cascade of neural networks; Computer vision; Convolution; Dictionaries; Estimation; human three-dimensional (3-D) system; Ill posed problems; Image reconstruction; neural network; Neural networks; Pose estimation; Shape; Three-dimensional displays; Two dimensional displays
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2018.2864824

Estimating three-dimensional (3-D) human poses from a given two-dimensional (2-D) shape is still an inherently ill-posed problem in computer vision. This paper proposes a method called cascade of multiple neural networks (CMNN) to solve this problem in following two steps: 1) create the initial estimated 3-D shape using the Zhou et al. method with a small number of basis shapes and 2) make this initial shape more alike to the original shape by using the CMNN. In comparing to existing works, the proposed method shows a significant outperformance in both accuracy and processing time. This paper also introduces a new system called Human3D that can estimate the 3-D pose of all people in a single RGB image. This system comprises two part: convolution pose machine (CPM) for estimating 2-D poses of all people in an RGB image and CMNN for reconstructing 3-D poses of them from outputs of the CPM.