Curtin University Homepage
  • Library
  • Help
    • Admin

    espace - Curtin’s institutional repository

    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item

    Multi-Scale Human Pose Tracking in 2D Monocular Images

    225495_144285_Multi_scale_human_pose_tracking.pdf (332.9Kb)
    Access Status
    Open access
    Authors
    Tian, J.
    Li, Ling
    Liu, Wan-Quan
    Date
    2014
    Type
    Journal Article
    
    Metadata
    Show full item record
    Citation
    Tian, J. and Li, L. and Liu, W. 2014. Multi-Scale Human Pose Tracking in 2D Monocular Images. Journal of Computer and Communications. 2: pp. 78-84.
    Source Title
    Journal of Computer and Communications
    DOI
    10.4236/jcc.2014.22014
    ISSN
    2327-5219
    School
    Department of Computing
    Remarks

    This open access article is distributed under the Creative Commons license http://creativecommons.org/licenses/by/4.0/

    URI
    http://hdl.handle.net/20.500.11937/13304
    Collection
    • Curtin Research Publications
    Abstract

    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

    Related items

    Showing items related by title, author, creator and subject.

    • Tracking human poses in various scales with accurate appearance
      Tian, J.; Lu, Y.; Li, L.; Liu, Wan-Quan (2017)
      Building a robust and fully automatic framework for human motion tracking in 2D images and videos remains a challenging task in computer vision due to cluttered backgrounds, self-occlusions, variations of body shape and ...
    • Model based methods for locating, enhancing and recognising low resolution objects in video
      Kramer, Annika (2009)
      Visual perception is our most important sense which enables us to detect and recognise objects even in low detail video scenes. While humans are able to perform such object detection and recognition tasks reliably, most ...
    • Human Pose Tracking from Monocular Image Sequences
      Tian, Jinglan (2016)
      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 ...
    Advanced search

    Browse

    Communities & CollectionsIssue DateAuthorTitleSubjectDocument TypeThis CollectionIssue DateAuthorTitleSubjectDocument Type

    My Account

    Admin

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Follow Curtin

    • 
    • 
    • 
    • 
    • 

    CRICOS Provider Code: 00301JABN: 99 143 842 569TEQSA: PRV12158

    Copyright | Disclaimer | Privacy statement | Accessibility

    Curtin would like to pay respect to the Aboriginal and Torres Strait Islander members of our community by acknowledging the traditional owners of the land on which the Perth campus is located, the Whadjuk people of the Nyungar Nation; and on our Kalgoorlie campus, the Wongutha people of the North-Eastern Goldfields.