%0 Conference Proceedings
%T Learning to Segment Humans by Stacking their Body Parts,
%A Eloi Puertas
%A Miguel Angel Bautista
%A Daniel Sanchez
%A Sergio Escalera
%A Oriol Pujol
%B ECCV Workshop on ChaLearn Looking at People
%D 2014
%V 8925
%F Eloi Puertas2014
%O HuPBA;MILAB
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2553), last updated on Tue, 18 Oct 2016 11:48:56 +0200
%X 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 bodypart likelihood maps. These likelihood maps are obtained in a first stageby 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.
%K Human body segmentation
%K Stacked Sequential Learning
%U http://refbase.cvc.uab.es/files/PBS2014.pdf
%U http://dx.doi.org/10.1007/978-3-319-16178-5_48
%P 685-697