Papers
arxiv:2104.05167

Egocentric Pose Estimation from Human Vision Span

Published on Apr 12, 2021
Authors:
,

Abstract

A deep learning system is presented for estimating body pose from wide-angle egocentric camera views by combining SLAM features with body shape imagery, enabling real-time tracking with geometric consistency constraints.

Estimating camera wearer's body pose from an egocentric view (egopose) is a vital task in augmented and virtual reality. Existing approaches either use a narrow field of view front facing camera that barely captures the wearer, or an extruded head-mounted top-down camera for maximal wearer visibility. In this paper, we tackle the egopose estimation from a more natural human vision span, where camera wearer can be seen in the peripheral view and depending on the head pose the wearer may become invisible or has a limited partial view. This is a realistic visual field for user-centric wearable devices like glasses which have front facing wide angle cameras. Existing solutions are not appropriate for this setting, and so, we propose a novel deep learning system taking advantage of both the dynamic features from camera SLAM and the body shape imagery. We compute 3D head pose, 3D body pose, the figure/ground separation, all at the same time while explicitly enforcing a certain geometric consistency across pose attributes. We further show that this system can be trained robustly with lots of existing mocap data so we do not have to collect and annotate large new datasets. Lastly, our system estimates egopose in real time and on the fly while maintaining high accuracy.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2104.05167 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2104.05167 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.