Scribd Logo
Upload

Welcome to Scribd!

  • 46 views

    X-Aid™ Telegra's Automatic Video Incident Detection

    Uploaded by

    focad346

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    X-Aid™ Telegra's Automatic Video Incident Detection

    Uploaded by

    focad346
    46 views8 pages

    Original Title

    Telegra x-aid

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    46 views8 pages

    X-Aid™ Telegra's Automatic Video Incident Detection

    Uploaded by

    focad346

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 8

    X-aid™

    Telegra's Automatic Video


    Incident Detection
    X-aid™
    X-aid™, Telegra's Automatic Video Incident Detection
    System, is the industry most innovative and precise AID sys-
    tem currently on the market. X-aid™'s leading edge is based
    on unique and the most advanced algorithms, including
    video recognition and object tracking, pattern recognition
    and foreground object recognition algorithms.

    Main purpose of Automatic Video Incident Detection


    System is to increase safety on the road.

    With hundreds of cameras deployed throughout


    highways and tunnels delivering the immense
    amount of information simultaneously, it is im-
    possible even for a group of human operators to
    monitor and evaluate the information effective-
    ly or efficiently. Reliable AID system is a must
    in such environments because it significantly
    improves the efficiency of traffic management
    systems. It automatically reports dangerous
    situations and irregular traffic conditions, such
    as fire or smoke in a tunnel, stopped vehicle,
    slow vehicle, driving in opposite direction, pe-
    destrians in traffic lanes, dropped cargo, or
    traffic congestion.
    Lack of AID system means not to have an infor-
    mation on time (or not to have it at all!) about
    various incidents on the road, e.g. collision.
    These could mean further accidents as a result
    of queue and/or consequentially other dam-
    ages.

    PERFORMANCE

    X-aid™ has superior detection performance


    compared to current video incident detec-
    tion systems on the market, due to use of own
    unique algorithms. Video Automatic Incident
    Detection quality is evident in these most im-
    portant AID parameters:
    · High Detection Ratio - the number of incidents

    PAGE 3
    detected to the actual number of incidents in a
    data set
    · Low False Alarm Ratio - the number of incor-
    rectly detected incidents to the number of all
    detected incidents
    X-aidTM

    Detection Ratio has direct effect on operators


    and concessionaires:
    · Not spotting a Wrong-Way Driving on time
    nearly always results in a head-on collision.
    This will cause road closure and consequently,
    loss of income from toll. In the worst-case
    scenario, it may end up with the loss of human
    lives.
    High immunity on all weather conditions

    · Smoke/fire detection through video incident cause the operator to stop paying attention
    detection is the fastest information to be re- and not react when there is a real need for
    ceived if fire occurs in the tunnel. Seconds reaction.
    matter in that situation and not having timely - Not reacting to an alarm can lead to seri-
    alarm will cause slow reaction on the incident ously deteriorated tunnel safety
    (e.g. if the tunnel is not closed on time more - The Management will be forced to in-
    vehicle and people will be involved in the in- crease the number of operators to moni-
    cident). This would cause serious implications tor all video streams simultaneously to
    such as: injuries, damage on infrastructure, prevent such situations
    cost of repair, cost of not having the tunnel in - The system will not be used to its full
    operation, etc. potential, which translates to irrational
    · Without an AID in place, a stopped vehicle, expense
    usually caused by an accident, won't be no- · State-of-the-art automatic procedures that
    ticed until the operator sees a queue on CCTV were deployed to help operating the highway/
    streams. Typically, an operator can’t moni- tunnel could become useless as their inputs
    tor video streams from all cameras deployed are false or even worse are causing the dam-
    simultaneously. As a result, the operator's age. In some cases false alarms could cause
    reaction will inevitably be delayed and might a complete road closure. Road closures
    result in further accidents. translate to direct financial losses (e.g. toll
    income loss, reopening costs, additional
    False Alarm is the most annoying phenom- working hours for highway crews, etc.), but
    enon related to AID today. Presence of False also indirect losses from bad publicity.
    Alarm causes: · Agitated Operators are unable to perform
    · Cry Wolf Syndrome - too many false alarms their duties properly, because of constant
    High immunity on scene shakiness

    harassment by false alarms. Agitated Opera- MOST ADVANCED VIDEO


    tors lose focus and might overlook a critical RECOGNITION AND INCIDENT
    alarm, skip procedural steps in emergencies,
    DETECTION TECHNOLOGY
    etc. in a tunnel is an operator that operates
    this sensitive and expensive construction not
    Traditionally, counting object was depen-
    being focused.
    dent on the vehicle path line within a camera
    zone, Smaller objects (i.e. motorcycles) could
    ENSURING TOP PERFORMANCE
    be missed by a camera if there was another
    vehicle in the same zone. X-aid™ artificial in-
    X-aid™ achieves both of the goals: low false
    telligence recognition algorithms and machine
    alarms ratio and high detection rate, through
    learning setup process assure that no vehicle is
    these most important features:
    missed, regardless of vehicle size or number of
    vehicles appearing within the configurable area
    · Use of own unique detection algorithms
    supervised by a camera. X-aid™ guarantees
    · X-aid™ is not affected by the most common

    PAGE 5
    high accuracy and the highest performance.
    causes of unreliable operations:
    - Camera Vibrations
    - Weather Conditions
    - Luminance Variations
    · Machine learning setup process and auto-
    matic calibration ensure that there is no
    X-aidTM

    need for periodic setup or calibration once


    the system is deployed.
    INTEGRATED IN topXview™
    PLATFORM

    X-aid™ Video incident detection module is an X-aid™ enables the user to configure the
    integrated part of topXview™. This enables responses as well as parameters for video
    X-aid™ to have the fastest and the most reli- incidents using the intuitive, user-friendly
    able responses to visually detectable incidents. topXview™ GUI, eliminating the need for
    Combined with topXview's configurable auto- switching between multiple platforms /
    mated procedures, X-aid™ becomes a must- systems.
    have life-saving tool for any responsible ITS
    owner.
    TECHNICAL CHARACTERISTICS

    Video Input · Analogue (PAL, NTSC) with encoders (MPEG4…)


    · Digital (IP) cameras
    · Video capture card
    · Video streams from topXview™ streaming server
    · X-aid is capable of decoding the most common video formats. This includes, but
    is not limited to, MPEG 1/2/4 (including H.264 / AVC), MJPEG, etc.
    · Multiple camera streams can be connected to a single AID analyzer. AID soft-
    ware detects events simultaneously from all cameras connected to the analyzer

    Detections · Location of the vehicle in the wrong direction


    · Location of stopped vehicle
    · Traffic Slowdown (traffic congestion, configurable, 10 km/h threshold)
    · Slow vehicle (speed threshold under which the vehicle is classified as slow is
    configurable by the user)
    · Pedestrian presence and location
    · Reduced or Loss of Visibility (smoke, fog, etc.)
    · Fire

    Statistics · Average Vehicle Speed (per interval)


    · Vehicle Volume (per interval)

    Error · Video Signal Loss


    Notification · Camera Displacement - camera has moved from its original position

    System Error · Video Analyzer Error


    PAGE 7
    Notification · Video Analyzer Communication Loss

    Configuration · Detection Zones


    · Traffic Direction
    · Events (alarms, statistics) for each zone
    X-aidTM

    · Camera Calibration Parameters


    · Enabling/disabling of events/statistics

    Operating · Windows
    System

    Integration · Completely integrated in topXview™ platform


    DISCLAIMER: The contents and information contained in this brochure are intended for general purpose
    only and should not be relied upon by any person as being complete or accurate. Telegra will not accept
    any liability suffered or incurred by any person arising out of or in connection with any reliance on the
    content of or information containing in this brochure. Unauthorized disclosure or copying of any or all
    of it may be unlawful.

    You might also like