Joint Human Pose Estimation and Stereo 3D Localization

We present an end-to-end trainable Neural Network architecture for stereo imaging that jointly locates and estimates human body poses in 3D. Our method defines a 2D pose for each human in a stereo pair of images and uses a correlation layer with a composite field to associate each left-right pair of joints. In the absence of a stereo pose dataset, we show that we can train our method with synthetic data only and test it on real-world images (\textit{i.e.}, our training stage is domain invariant). Our method is particularly suitable for autonomous vehicles. We achieve state-of-the-art results for the 3D localization task on the challenging real-world KITTI dataset while running four times faster.

Presented at:
International Conference on Robotics and Automation (ICRA), paris, france, May 31th, June 4th 2020
Jun 01 2020
Additional link:

Note: The status of this file is:

 Record created 2020-02-13, last modified 2020-03-22

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)