A robust framework for 2D human pose tracking with spatial and temporal constraints
We work on the task of 2D articulated human pose tracking in monocular image sequences, an extremely challenging task due to background cluttering, variation in body appearance, occlusion and imaging conditions. Most of current approaches only deal with simple appearance and $adjacent$ body part dep...
| Main Authors: | , , |
|---|---|
| Format: | Conference Paper |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2015
|
| Online Access: | http://hdl.handle.net/20.500.11937/32211 |
| _version_ | 1848753598684463104 |
|---|---|
| author | Tian, J. Li, Ling Liu, Wan-Quan |
| author_facet | Tian, J. Li, Ling Liu, Wan-Quan |
| author_sort | Tian, J. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | We work on the task of 2D articulated human pose tracking in monocular image sequences, an extremely challenging task due to background cluttering, variation in body appearance, occlusion and imaging conditions. Most of current approaches only deal with simple appearance and $adjacent$ body part dependencies, especially the Gaussian tree-structured priors assumed over body part connections. Such prior makes the part connections independent to image evidence and in turn severely limits accuracy. Building on the successful pictorial structures model, we propose a novel framework combining an image-conditioned model that incorporates higher order dependencies of multiple body parts. In order to establish the conditioning variables, we employ the effective poselet features. In addition to this, we introduce a full body detector as the first step of our framework to reduce the search space for pose tracking. We evaluate our framework on two challenging image sequences and conduct a series of comparison experiments to compare the performance with another two approaches. The results illustrate that the proposed framework in this work outperforms the state-of-the-art 2D pose tracking systems. |
| first_indexed | 2025-11-14T08:27:04Z |
| format | Conference Paper |
| id | curtin-20.500.11937-32211 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:27:04Z |
| publishDate | 2015 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-322112017-09-13T15:18:38Z A robust framework for 2D human pose tracking with spatial and temporal constraints Tian, J. Li, Ling Liu, Wan-Quan We work on the task of 2D articulated human pose tracking in monocular image sequences, an extremely challenging task due to background cluttering, variation in body appearance, occlusion and imaging conditions. Most of current approaches only deal with simple appearance and $adjacent$ body part dependencies, especially the Gaussian tree-structured priors assumed over body part connections. Such prior makes the part connections independent to image evidence and in turn severely limits accuracy. Building on the successful pictorial structures model, we propose a novel framework combining an image-conditioned model that incorporates higher order dependencies of multiple body parts. In order to establish the conditioning variables, we employ the effective poselet features. In addition to this, we introduce a full body detector as the first step of our framework to reduce the search space for pose tracking. We evaluate our framework on two challenging image sequences and conduct a series of comparison experiments to compare the performance with another two approaches. The results illustrate that the proposed framework in this work outperforms the state-of-the-art 2D pose tracking systems. 2015 Conference Paper http://hdl.handle.net/20.500.11937/32211 10.1109/DICTA.2014.7008091 Institute of Electrical and Electronics Engineers Inc. restricted |
| spellingShingle | Tian, J. Li, Ling Liu, Wan-Quan A robust framework for 2D human pose tracking with spatial and temporal constraints |
| title | A robust framework for 2D human pose tracking with spatial and temporal constraints |
| title_full | A robust framework for 2D human pose tracking with spatial and temporal constraints |
| title_fullStr | A robust framework for 2D human pose tracking with spatial and temporal constraints |
| title_full_unstemmed | A robust framework for 2D human pose tracking with spatial and temporal constraints |
| title_short | A robust framework for 2D human pose tracking with spatial and temporal constraints |
| title_sort | robust framework for 2d human pose tracking with spatial and temporal constraints |
| url | http://hdl.handle.net/20.500.11937/32211 |