• DocumentCode
    693801
  • Title

    Rectified Trajectory Analysis Based Abnormal Loitering Detection for Video Surveillance

  • Author

    Jong-Gook Ko ; Jang-Hee Yoo

  • Author_Institution
    Video Surveillance Res. Sect., Electron. & Telecommun. Res. Inst., Daejeon, South Korea
  • fYear
    2013
  • fDate
    3-5 Dec. 2013
  • Firstpage
    289
  • Lastpage
    293
  • Abstract
    Trajectory analysis for detection of abnormal loitering has attracted significant research interest in recent years. We present a new approach for abnormal loitering detection using trajectory analysis. Trajectory Direction History Analysis method is proposed to detect abnormal loitering and Inverse Perspective Mapping (IPM) is presented to resolve distortion of trajectory direction because of perspective effect. Proposed loitering detection method has shown good performance.
  • Keywords
    behavioural sciences computing; object detection; video surveillance; IPM; abnormal behavior detection; abnormal loitering detection; inverse perspective mapping; rectified trajectory analysis; trajectory direction distortion; trajectory direction history analysis method; video surveillance; Hidden Markov models; History; Trajectory; Vectors; Video surveillance; Visualization; Abnormal Behavior Detection; Video Surveillance;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Artificial Intelligence, Modelling and Simulation (AIMS), 2013 1st International Conference on
  • Conference_Location
    Kota Kinabalu
  • Print_ISBN
    978-1-4799-3250-4
  • Type

    conf

  • DOI
    10.1109/AIMS.2013.53
  • Filename
    6959931