Configuring grids for object detection scenarios - KiwiVision™ 4.1 GA

KiwiVision™ Video Analytics Guide 4.1 GA

series
KiwiVision™ 4.1 GA
revised_modified
2019-07-10

You can configure the grid of a scene so that changes in the scene can be properly detected and analyzed.

What you should know

  • Object detection and Stopped vehicle detection scenarios only use perspective grids.
  • Custom Object Detector scenarios can use fixed grids or perspective grids.

    Fixed grids are used for top-down scenes, where there is no horizon, for example, the top view of a parking lot.

NOTE: Depending on which type of scenario you are configuring, some settings might be unavailable or hidden if Advanced mode is disabled. When Advanced mode is enabled, the advanced settings are displayed in bold.

Procedure

  1. From the Config Tool home page, open the Video task.
  2. From the area view, select a camera that you applied an analytics scenario to.
  3. Click the Video analytics tab, and then click the scenario you want to configure.
  4. Click the Grid tab.
  5. For a perspective grid, use one object in the video as a size reference to configure the near and far objects:
    1. When the reference object is placed near to the camera, click and drag the Near object over the reference object in the video.
    2. Adjust the height of the Near object to match the height of the reference object by clicking and dragging the white dot on the Near object.
    3. Repeat the previous two steps using the Far object when the same reference object is placed far from the camera.
  6. For a fixed grid, adjust the height of the Object to match the height of a reference object by clicking and dragging the white dot on the Object.
  7. In the Grid section, configure the following settings:
    NOTE: Changing the block size affects the size of the blocks displayed when you enable the Show detection grid option in the area configuration.
    Block size
    The size of analysis units relative to the specified object or person size in the image. If you set a low value, the required computing power increases, but the distinction between different object sizes in the image is more accurate.
    Min. block size
    The minimum size of analysis units relative to the height or width of the video, depending on which measurement is shorter.
  8. Click Apply.