Human Pose Tracking from Monocular Image Sequences

This thesis proposes various novel approaches for improving the performance of automatic 2D human pose tracking system including multi-scale strategy, mid-level spatial dependencies to constrain more relations of multiple body parts, additional constraints between symmetric body parts and the left/r...

Full description

Bibliographic Details
Main Author: Tian, Jinglan
Format: Thesis
Published: Curtin University 2016
Online Access:http://hdl.handle.net/20.500.11937/51721
_version_ 1848758139857403904
author Tian, Jinglan
author_facet Tian, Jinglan
author_sort Tian, Jinglan
building Curtin Institutional Repository
collection Online Access
description This thesis proposes various novel approaches for improving the performance of automatic 2D human pose tracking system including multi-scale strategy, mid-level spatial dependencies to constrain more relations of multiple body parts, additional constraints between symmetric body parts and the left/right confusion correction by a head orientation estimator. These proposed approaches are employed to develop a complete human pose tracking system. The experimental results demonstrate significant improvements of all the proposed approaches towards accuracy and efficiency.
first_indexed 2025-11-14T09:39:15Z
format Thesis
id curtin-20.500.11937-51721
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:39:15Z
publishDate 2016
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-517212017-03-28T04:33:53Z Human Pose Tracking from Monocular Image Sequences Tian, Jinglan This thesis proposes various novel approaches for improving the performance of automatic 2D human pose tracking system including multi-scale strategy, mid-level spatial dependencies to constrain more relations of multiple body parts, additional constraints between symmetric body parts and the left/right confusion correction by a head orientation estimator. These proposed approaches are employed to develop a complete human pose tracking system. The experimental results demonstrate significant improvements of all the proposed approaches towards accuracy and efficiency. 2016 Thesis http://hdl.handle.net/20.500.11937/51721 Curtin University fulltext
spellingShingle Tian, Jinglan
Human Pose Tracking from Monocular Image Sequences
title Human Pose Tracking from Monocular Image Sequences
title_full Human Pose Tracking from Monocular Image Sequences
title_fullStr Human Pose Tracking from Monocular Image Sequences
title_full_unstemmed Human Pose Tracking from Monocular Image Sequences
title_short Human Pose Tracking from Monocular Image Sequences
title_sort human pose tracking from monocular image sequences
url http://hdl.handle.net/20.500.11937/51721