Home
Resource
Hybrid discriminative-generative methods for human pose reconstruction from monocular imagery
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(13.03 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Dilsizian, Mark. Hybrid discriminative-generative methods for human pose reconstruction from monocular imagery. Retrieved from https://doi.org/doi:10.7282/T3DR2XNV

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleHybrid discriminative-generative methods for human pose reconstruction from monocular imagery
NameDilsizian, Mark (author); Metaxas, Dimitris (chair); Kulikowski, Casimir (internal member); Elgammal, Ahmed (internal member); Tsechpenakis, Gavriil (outside member); Rutgers University; Graduate School - New Brunswick
Date Created2016
Other Date2016-05 (degree)
SubjectComputer Science, Computer vision
Extent1 online resource (xii, 100 p. : ill.)
DescriptionEstimating 3D human pose from monocular images is an important and challenging problem in computer vision with numerous applications including human-computer interaction, human activity recognition, biomechanical analysis, and security. Existing state-of-the-art methods utilize statistical learning models that are inherently limited because they require sufficient training data that does not often include uncommon pose articulations or subject proportions. In addition, these methods often return global average case results and cannot easily leverage anthropomorphic, kinematic, and other physics-based constraints. However, a prior model-based search can be computationally prohibitive due to the combinatorially large set of plausible joint combinations. We combine statistical learning-based approaches with a prior part-based model into a hybrid constrained optimization that leverages strengths of both approaches. The method guarantees a plausible human pose while also resolving local ambiguities among body parts. Qualitative evaluation of the proposed methods on human pose datasets show improvement in reconstruction accuracy compared to current state-of-the-art methods.
NotePh.D.
NoteIncludes bibliographical references
Noteby Mark Dilsizian
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/T3DR2XNV
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024