A very simple framework for 3D human poses estimation using a single 2D image: Comparison of geometric moments descriptors

作者：

Highlights：

• 3D human pose estimation from a single image is an important problem.

• We use geometric moments to analyse the silhouette of human extracted from single image and make comparison between different geometrics moments (Krawtchouk, Hanh, Zernike and Hu).

• We prove that by using a very simple framework we are able to extract the 3D posture of a human with a single 2D image in real time.

• We generate the learning dataset with Blender, an open source software publicly available, by using motion capture data.

摘要

•3D human pose estimation from a single image is an important problem.•We use geometric moments to analyse the silhouette of human extracted from single image and make comparison between different geometrics moments (Krawtchouk, Hanh, Zernike and Hu).•We prove that by using a very simple framework we are able to extract the 3D posture of a human with a single 2D image in real time.•We generate the learning dataset with Blender, an open source software publicly available, by using motion capture data.

论文关键词：3D Pose estimation,3D modeling,Skeleton extraction,Shape descriptor,Geometric moment,Krawtchouk moment,Zernike moment,Hu moment,Hahn moment

论文评审过程：Received 15 December 2016, Revised 3 May 2017, Accepted 16 June 2017, Available online 17 June 2017, Version of Record 12 July 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.024