• DocumentCode
    3003511
  • Title

    Hydra: multiple people detection and tracking using silhouettes

  • Author

    Haritaoglu, Ismail ; Harwood, David ; Davis, Larry S.

  • Author_Institution
    Comput. Vision Lab., Maryland Univ., College Park, MD, USA
  • fYear
    1999
  • fDate
    36342
  • Firstpage
    6
  • Lastpage
    13
  • Abstract
    Hydra, is a real-time system for detecting and tracking multiple people when they appear in a group. We describe the computational models employed by Hydra to track multiple people before, during and after occlusion. Hydra combines a silhouette-based shape model, a motion model, and correlation-based matching methods to classify whether or not a foreground region contains multiple people, and to segment the region into its constituent people and track them. Experimental results demonstrate robustness and real-time performance of the algorithm
  • Keywords
    image matching; image motion analysis; image segmentation; object detection; real-time systems; tracking; Hydra; computational models; correlation-based matching methods; motion model; multiple people detection; occlusion; real-time performance; real-time system; silhouette-based shape model; silhouettes; tracking; Histograms; Motion detection; Motion estimation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Visual Surveillance, 1999. Second IEEE Workshop on, (VS'99)
  • Conference_Location
    Fort Collins, CO
  • Print_ISBN
    0-7695-0037-4
  • Type

    conf

  • DOI
    10.1109/VS.1999.780263
  • Filename
    780263