PT Unknown
AU Eloi Puertas
   Miguel Angel Bautista
   Daniel Sanchez
   Sergio Escalera
   Oriol Pujol
TI Learning to Segment Humans by Stacking their Body Parts,
BT ECCV Workshop on ChaLearn Looking at People
PY 2014
BP 685
EP 697
VL 8925
DI 10.1007/978-3-319-16178-5_48
DE Human body segmentation; Stacked Sequential Learning
AB 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.
ER