• DocumentCode
    2817464
  • Title

    Video-based multi-agent traffic surveillance system

  • Author

    Abreu, Bruno ; Botelho, Luis ; Cavallaro, Andrea ; Douxchamps, Damien ; Ebrahimi, Touradj ; Figueiredo, Pedro ; Macq, Benoit ; Mory, Benoit ; Nunes, Luis ; Orri, Javier ; Trigueiros, Maria José ; Violante, Ana

  • fYear
    2000
  • fDate
    2000
  • Firstpage
    457
  • Lastpage
    462
  • Abstract
    This paper describes Monitorix, a video-based traffic surveillance multi-agent system. Monitorix agents are grouped in four tiers, according to the kind of information processing they perform: the sensors and effectors tier, the objective description tier, the application assistant tier, and the user assistant tier. The video analysis algorithms use an adaptive, data-driven, application independent approach to extract features from the video raw data. In spite of the diversity of agent tasks, adaptive learning algorithms are used in most cases. The integration of video analysis algorithms and agent technology is made via a special middle agent called Proxy. Monitorix is a fully decentralised multi-agent system living in a FIPA Platform and using FIPA Agent Communication Language. Tracking of vehicles across nonoverlapping cameras is performed by the Tracker agent, using a traffic model and learning algorithms that tune the model parameters
  • Keywords
    computer vision; feature extraction; learning (artificial intelligence); multi-agent systems; road traffic; surveillance; traffic engineering computing; FIPA Agent Communication Language; FIPA Platform; Monitorix; Proxy; Tracker agent; adaptive data-driven application-independent approach; adaptive learning algorithms; agent task diversity; agent technology; application assistant tier; feature extraction; fully decentralised multiagent system; middle agent; nonoverlapping cameras; objective description tier; sensor-effector tier; user assistant tier; video analysis algorithms; video-based multiagent traffic surveillance system; Algorithm design and analysis; Cameras; Data mining; Feature extraction; Information processing; Monitoring; Multiagent systems; Sensor phenomena and characterization; Surveillance; Vehicles;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Vehicles Symposium, 2000. IV 2000. Proceedings of the IEEE
  • Conference_Location
    Dearborn, MI
  • Print_ISBN
    0-7803-6363-9
  • Type

    conf

  • DOI
    10.1109/IVS.2000.898385
  • Filename
    898385