Learning to Segment Humans by Stacking Their Body Parts
Abstract
Human segmentation in still images is a complex task due to the wide range of body poses and drastic changes in environmental conditions. Usually, human body segmentation is treated in a two-stage fashion. First, a human body part detection step is performed, and then, human part detections are used as prior knowledge to be optimized by segmentation strategies. In this paper, we present a two-stage scheme based on Multi-Scale Stacked Sequential Learning (MSSL). We define an extended feature set by stacking a multi-scale decomposition of body part likelihood maps. These likelihood maps are obtained in a first stage by means of a ECOC ensemble of soft body part detectors. In a second stage, contextual relations of part predictions are learnt by a binary classifier, obtaining an accurate body confidence map. The obtained confidence map is fed to a graph cut optimization procedure to obtain the final segmentation. Results show improved segmentation when MSSL is included in the human segmentation pipeline.
Cite
Text
Puertas et al. "Learning to Segment Humans by Stacking Their Body Parts." European Conference on Computer Vision Workshops, 2014. doi:10.1007/978-3-319-16178-5_48Markdown
[Puertas et al. "Learning to Segment Humans by Stacking Their Body Parts." European Conference on Computer Vision Workshops, 2014.](https://mlanthology.org/eccvw/2014/puertas2014eccvw-learning/) doi:10.1007/978-3-319-16178-5_48BibTeX
@inproceedings{puertas2014eccvw-learning,
title = {{Learning to Segment Humans by Stacking Their Body Parts}},
author = {Puertas, Eloi and Bautista, Miguel Ángel and Sánchez, Daniel and Escalera, Sergio and Pujol, Oriol},
booktitle = {European Conference on Computer Vision Workshops},
year = {2014},
pages = {685-697},
doi = {10.1007/978-3-319-16178-5_48},
url = {https://mlanthology.org/eccvw/2014/puertas2014eccvw-learning/}
}