Analyse du mouvement humain par vison artificielle pour consoles de jeux vidéos

Authors: Hanafi, Maher
Advisor: Zaccarin, André
Abstract: This report is interested in the markerless motion tracking and the three-dimensional reconstruction of articulated human movements from video sequences acquired with a 3D camera (stereo or infrared). Nowadays, this research field is very active and contains a wide field of applications which deals with areas such as motion capture for animations and virtual reality without using any kind of markers, human-machine interaction (HMI), remote monitoring and of course video games. In this manuscript, we propose a novel method to estimate the 3D human pose. This markerless technique is based on an alignment of a skeleton and a 3D human model over the silhouette seen by the camera by leaning on a progressive adjustment, starting from the head and continuing to the trunk and the various members. The technique considers the articulated aspect of the human body and allows, in particular, solving some problems of occlusions and overlapping. Besides, the complexity of the human body structure, of its physical constraints as well as the big variability in the images’ observations, makes that the solution determination for this problem is difficult. The objective of this memory thus is to develop a strong and robust method capable of facing these various difficulties imposed by the technology choice and the general context of use for home video games consoles. To approach this study, we propose a 3D human model which takes into account physical and kinematic constraints and which allows a coherent integration of various visual information such as face detection, edges and silhouettes. The combined system allows 3D human motion tracking using only one 3D camera.
Document Type: Mémoire de maîtrise
Issue Date: 2012
Open Access Date: 18 April 2018
Permalink: http://hdl.handle.net/20.500.11794/23489
Grantor: Université Laval
Collection:Thèses et mémoires

Files in this item:
SizeFormat 
28483.pdf11.46 MBAdobe PDFView/Open
All documents in CorpusUL are protected by Copyright Act of Canada.