Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/103966
Title: Human body parts segmentation via stacked and multi-task learning
Author: Sánchez Abril, Daniel
Director: Escalera, Sergio  
Baró, Xavier  
Abstract: The segmentation of people in RGB images poses a key obstacle in the field of computer vision. In our thesis, we tackle this issue through hand-crafted features in a two-stage pipeline, targeting both binary and multiple body part segmentation. For our purposes, we employ tools such as AdaBoost, support vector machines, Haar-like features, histograms of oriented gradients and graphics. We also address the differences between cascade learning and stacked learning. Finally, we analyse a multimodal approach to combining different tasks, which allows us to improve and refine our predictions concerning the segmentation of body parts using 2D and 3D estimations of posture and depth, a feat made possible thanks to deep learning.
Keywords: segmentation
body parts
stacked learning
multi-task
Document type: info:eu-repo/semantics/doctoralThesis
Issue Date: 9-Oct-2019
Publication license: http://creativecommons.org/licenses/by-nc-sa/3.0/es/  
Appears in Collections:Tesis doctorals

Files in This Item:
File Description SizeFormat 
phd_thesis_dani-1.pdfSánchez_Abril_dissertation13,22 MBAdobe PDFThumbnail
View/Open