Search:
Computing and Library Services - delivering an inspiring information environment

Fast human detection for video event recognition

Wang, J, Xu, Zhijie and Hoder, M.E. (2009) Fast human detection for video event recognition. In: Proceedings of Computing and Engineering Annual Researchers' Conference 2009: CEARC’09. University of Huddersfield, Huddersfield, pp. 70-75. ISBN 9781862180857

[img] PDF - Published Version
Download (332kB)

    Abstract

    Human body detection, which has become a research hotspot during the last two years, can be used in many video content analysis applications. This paper investigates a fast human detection method for volume based video event detection. Compared with other object detection systems, human body detection brings more challenge due to threshold problems coming from a wide range of dynamic properties. Motivated by approaches successfully introduced in facial recognition applications, it adapts and adopts feature extraction and machine learning mechanism to classify certain areas from video frames. This method starts from the extraction of Haar-like features from large numbers of sample images for well-regulated feature distribution and is followed by AdaBoost learning and detection algorithm for pattern classification. Experiment on the classifier proves the Haar-like feature based machine learning mechanism can provide a fast and steady result for human body detection and can be further applied to reduce negative aspects in human modelling and analysis for volume based event detection.

    Item Type: Book Chapter
    Uncontrolled Keywords: Human detection; Haar-like features; AdBoosts learning algorithm
    Subjects: T Technology > T Technology (General)
    Schools: School of Computing and Engineering
    School of Computing and Engineering > Computing and Engineering Annual Researchers' Conference (CEARC)
    School of Computing and Engineering > Computer Graphics, Imaging and Vision Research Group
    Related URLs:
    Depositing User: Sharon Beastall
    Date Deposited: 27 Jan 2010 12:11
    Last Modified: 05 Jan 2011 12:42
    URI: http://eprints.hud.ac.uk/id/eprint/6864

    Document Downloads

    Downloader Countries

    More statistics for this item...

    Item control for Repository Staff only:

    View Item

    University of Huddersfield, Queensgate, Huddersfield, HD1 3DH Copyright and Disclaimer All rights reserved ©