Human body tracking and pose estimation from monocular image sequences
This thesis describes a bottom-up approach to estimating human pose over time based on monocular views with no restriction on human activities,Three approaches are proposed to address the weaknesses of existing approaches, including building a specific appearance model using clustering,utilising bot...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Curtin University
2013
|
| Online Access: | http://hdl.handle.net/20.500.11937/1665 |
| _version_ | 1848743732940111872 |
|---|---|
| author | Lu, Yao |
| author_facet | Lu, Yao |
| author_sort | Lu, Yao |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This thesis describes a bottom-up approach to estimating human pose over time based on monocular views with no restriction on human activities,Three approaches are proposed to address the weaknesses of existing approaches, including building a specific appearance model using clustering,utilising both the generic and specific appearance models in the estimation, and building an uncontaminated appearance model by removing backgroundpixels from the training samples. Experimental results show that the proposed system outperforms existing system significantly. |
| first_indexed | 2025-11-14T05:50:15Z |
| format | Thesis |
| id | curtin-20.500.11937-1665 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T05:50:15Z |
| publishDate | 2013 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-16652017-02-20T06:38:47Z Human body tracking and pose estimation from monocular image sequences Lu, Yao This thesis describes a bottom-up approach to estimating human pose over time based on monocular views with no restriction on human activities,Three approaches are proposed to address the weaknesses of existing approaches, including building a specific appearance model using clustering,utilising both the generic and specific appearance models in the estimation, and building an uncontaminated appearance model by removing backgroundpixels from the training samples. Experimental results show that the proposed system outperforms existing system significantly. 2013 Thesis http://hdl.handle.net/20.500.11937/1665 en Curtin University fulltext |
| spellingShingle | Lu, Yao Human body tracking and pose estimation from monocular image sequences |
| title | Human body tracking and pose estimation from monocular image sequences |
| title_full | Human body tracking and pose estimation from monocular image sequences |
| title_fullStr | Human body tracking and pose estimation from monocular image sequences |
| title_full_unstemmed | Human body tracking and pose estimation from monocular image sequences |
| title_short | Human body tracking and pose estimation from monocular image sequences |
| title_sort | human body tracking and pose estimation from monocular image sequences |
| url | http://hdl.handle.net/20.500.11937/1665 |