Configuring Video Analytics Cameras

Cameras with video analytics and cameras connected to ACC ES Analytics Appliances can be configured to better understand the scene where it is installed and improve the accuracy of the camera's classified object detection. This allows cameras to learn their surroundings and detect specific events.

To configure Classified Object Motion Detection for a video analytics camera, see Setting Up Classified Object Motion Detection.

NOTE: The dialog box may appear differently depending on the device. Options that are not supported by the device will be disabled or hidden.

  1. In the device Setup tab, click .

    The Settings dialog box opens.

  2. From the Analytics Scene Mode: drop down list, select the location that best describes where the camera is installed.

    The Analytics Scene Mode: setting helps the camera identify what it should be looking for.

    • Outdoor —  this option is suitable for most outdoor environments. This setting optimizes the camera to identify vehicles and people.
    • Outdoor High Sensitivity — only use this option if you require the system to be more sensitive than the Outdoor setting. This option is optimized to run with higher sensitivity for detecting people and vehicles in challenging outdoor scenes. Be aware that this option will generate more false positives.
    • Large Indoor Area — this option only detects people and is optimized to detect people around obstructions, like chairs and desks, if the head and torso are visible.
    • Indoor Overhead — this option is optimized for cameras mounted directly overhead and should only be used when a torso cannot be seen in the camera FoV. Any movement is assumed to be human. It can be used in areas with limited space but with high ceilings, or to monitor doors. It should not be used with the Avigilon Appearance Search feature, or to detect people traveling against the crowd.

    NOTE: If you change the Analytics Scene Mode: setting after it has been set, the system will delete any data the device may have learned.

  3. In the Self Learning section:
    1. Check the Enable box to enable self-learning.
    2. Clear the check box to disable self-learning. After self-learning is disabled, the camera stops self-learning and no longer utilizes any learned information.

      NOTE: Disabling self-learning may result in more classified objects being falsely detected.

    3. The Progress: status in the dialog box tells you the progress made so far.
    4. To reset self-learning, click Reset.
      • In the confirmation dialog box that appears, click Yes.

      NOTE: When self-learning is reset, all previous self-learning data for the device is deleted.

  4. In the Camera Type: drop down list, select the type of camera that has been connected to this camera channel.

    This helps the video analytics determine what type of image it should expect from the camera.

    • Day and Night — select this option if the camera can stream video in color or black and white. This type of camera typically displays color video during the day and black and white video at night to capture as much detail as it can of the scene.
    • Color — select this option if the camera can only stream video in color.
    • Black and White — select this option if the camera can only stream video in black and white.
    • Thermal — select this option if the camera can stream forward looking infrared (FLIR) video.
  5. Move the Sensitivity: slider to define how sensitive the camera is to sudden changes in the scene.

    Tampering is defined as a sudden change in the camera field of view, usually caused by someone unexpectedly moving the camera. Lower the setting if small changes in the scene, like moving shadows, cause tampering events. If the camera is installed indoors and the scene is unlikely to change, you can increase the setting to capture more unusual events.

  6. Select the Trigger Delay: value to define how long the camera will wait for tampering events to be sent.

    Trigger delay is defined as a temporary change in the camera field of view that may generate a tampering event due to a change in the scene. If the tampering ends before the trigger delay time has elapsed, no tampering events will be sent. If the time elapses but the tampering has not stopped, the events will be sent by the camera. The default setting is 8 and is a value in seconds from 1 and 30.

  7. Select the Enable Appearance Search check box if you want to use this camera with the Avigilon Appearance Search feature.

    NOTE: This option is only displayed if the camera is connected to a network video recorder that supports the Avigilon Appearance Search feature.

  8. If the camera is too sensitive and falsely detects motion as classified objects, select the Enable Noise Filter check box .

    Disable this option if the camera is not sensitive enough.

  9. Click Apply to save your settings.

Next, you can enable self-learning and configure analytics events. For more information, see Self-Learning on Video Analytics Devices or Analytic Events

 

 

Avigilon Control Center 6.6 | 20170922