Please use this identifier to cite or link to this item: https://hdl.handle.net/10216/78474
Author(s): Maria João M. Vasconcelos
João Manuel R. S. Tavares
Title: Human motion segmentation using active shape models
Issue Date: 2015
Abstract: Human motion analysis from images is meticulously related to thedevelopment of computational techniques capable of automatically identifying,tracking and analyzing relevant structures of the body. This work explores theidentification of such structures in images, which is the first step of any computationalsystem designed to analyze human motion. A widely used database(CASIA Gait Database) was used to build a Point Distribution Model (PDM) of thestructure of the human body. The training dataset was composed of 14 subjectswalking in four directions, and each shape was represented by a set of 113 labelledlandmark points. These points were composed of 100 contour points automaticallyextracted from the silhouette combined with an additional 13 anatomical pointsfrom elbows, knees and feet manually annotated. The PDM was later used in theconstruction of an Active Shape Model, which combines the shape model with graylevel profiles, in order to segment the modelled human body in new images. Theexperiments with this segmentation technique revealed very encouraging results asit was able to gather the necessary data of subjects walking in different directionsusing just one segmentation model.
Subject: Ciências Tecnológicas, Ciências da engenharia e tecnologias
Technological sciences, Engineering and technology
Scientific areas: Ciências da engenharia e tecnologias
Engineering and technology
URI: https://repositorio-aberto.up.pt/handle/10216/78474
Source: Computational and experimental biomedical sciences: methods and applications
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: openAccess
License: https://creativecommons.org/licenses/by-nc/4.0/
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
100458.pdfPaper1.65 MBAdobe PDFThumbnail
View/Open


This item is licensed under a Creative Commons License Creative Commons