Multi-Scale Human Pose Tracking in 2D Monocular Images
In this paper we address the problem of tracking human poses in multiple perspective scales in 2D monocular images/videos. In most state-of-the-art 2D tracking approaches, the issue of scale variation is rarely discussed. However in reality, videos often contain human motion with dynamically changed...
| Main Authors: | , , |
|---|---|
| Format: | Journal Article |
| Published: |
Scientific Research Publishing, Inc
2014
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/13304 |
| _version_ | 1848748311957209088 |
|---|---|
| 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 | In this paper we address the problem of tracking human poses in multiple perspective scales in 2D monocular images/videos. In most state-of-the-art 2D tracking approaches, the issue of scale variation is rarely discussed. However in reality, videos often contain human motion with dynamically changed scales. In this paper we pro-pose a tracking framework that can deal with this problem. A scale checking and adjusting algorithm is pro-posed to automatically adjust the perspective scales during the tracking process. Two metrics are proposed for detecting and adjusting the scale change. One metric is from the height value of the tracked target, which is suitable for some sequences where the tracked target is upright and with no limbs stretching. The other metric employed in this algorithm is more generic, which is invariant to motion types. It is the ratio between the pixel counts of the target silhouette and the detected bounding boxes of the target body. The proposed algorithm is tested on the publicly available datasets (HumanEva). The experimental results show that our method demon-strated higher accuracy and efficiency compared to state-of-the-art approaches |
| first_indexed | 2025-11-14T07:03:02Z |
| format | Journal Article |
| id | curtin-20.500.11937-13304 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:03:02Z |
| publishDate | 2014 |
| publisher | Scientific Research Publishing, Inc |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-133042017-09-13T14:59:51Z Multi-Scale Human Pose Tracking in 2D Monocular Images Tian, J. Li, Ling Liu, Wan-Quan Human Motion Tracking Monocular Video 2D Multi-Scale In this paper we address the problem of tracking human poses in multiple perspective scales in 2D monocular images/videos. In most state-of-the-art 2D tracking approaches, the issue of scale variation is rarely discussed. However in reality, videos often contain human motion with dynamically changed scales. In this paper we pro-pose a tracking framework that can deal with this problem. A scale checking and adjusting algorithm is pro-posed to automatically adjust the perspective scales during the tracking process. Two metrics are proposed for detecting and adjusting the scale change. One metric is from the height value of the tracked target, which is suitable for some sequences where the tracked target is upright and with no limbs stretching. The other metric employed in this algorithm is more generic, which is invariant to motion types. It is the ratio between the pixel counts of the target silhouette and the detected bounding boxes of the target body. The proposed algorithm is tested on the publicly available datasets (HumanEva). The experimental results show that our method demon-strated higher accuracy and efficiency compared to state-of-the-art approaches 2014 Journal Article http://hdl.handle.net/20.500.11937/13304 10.4236/jcc.2014.22014 Scientific Research Publishing, Inc fulltext |
| spellingShingle | Human Motion Tracking Monocular Video 2D Multi-Scale Tian, J. Li, Ling Liu, Wan-Quan Multi-Scale Human Pose Tracking in 2D Monocular Images |
| title | Multi-Scale Human Pose Tracking in 2D Monocular Images |
| title_full | Multi-Scale Human Pose Tracking in 2D Monocular Images |
| title_fullStr | Multi-Scale Human Pose Tracking in 2D Monocular Images |
| title_full_unstemmed | Multi-Scale Human Pose Tracking in 2D Monocular Images |
| title_short | Multi-Scale Human Pose Tracking in 2D Monocular Images |
| title_sort | multi-scale human pose tracking in 2d monocular images |
| topic | Human Motion Tracking Monocular Video 2D Multi-Scale |
| url | http://hdl.handle.net/20.500.11937/13304 |