The objective of this work is to segment human body parts from egocentric video using semantic segmentation networks. Our contribution is two-fold: i) we create a semi-synthetic dataset composed of more than 15, 000 realistic images and associated pixel-wise labels of egocentric human body parts, such as arms or legs including different demographic factors; ii) building upon the ThunderNet architecture, we implement a deep learning semantic segmentation algorithm that is able to perform beyond real-time requirements (16 ms for 720 x 720 images). It is believed that this method will enhance sense of presence of Virtual Environments and will constitute a more realistic solution to the standard virtual avatars.
@article{arxiv.2005.12074,
title = {Egocentric Human Segmentation for Mixed Reality},
author = {Andrija Gajic and Ester Gonzalez-Sosa and Diego Gonzalez-Morin and Marcos Escudero-Viñolo and Alvaro Villegas},
journal= {arXiv preprint arXiv:2005.12074},
year = {2020}
}
Comments
Accepted for presentation at EPIC@CVPR2020 workshop