Configuring the area for the Area protection and Direction control scenarios - KiwiVision™ 4.7.1 | Security Center 5.11.2.0

KiwiVision™ User Guide for Security Center 5.11.2.0
Product
KiwiVision™
Content type
Guides > User guides
Version
4.7
Release
4.7.1
Language
English
Last updated
2023-02-03

You can define areas in the video to trigger events when a person is detected in those areas.

What you should know

  • In intrusion detection scenarios, an area is an alarm region. You can define multiple areas in a scenario to monitor for intrusion. Settings are configured per area.
  • You can enable the Show movement grid option to visualize the sensitivity of your configuration. This option displays the analysis blocks that make up an area in different colors to show when they are active, and when the velocity, path deviation, and travel distance is properly detected.
NOTE: Depending on which scenario type you are configuring, some settings might be unavailable or hidden if Advanced mode is disabled.
Best practices
  • If the scene requires to capture small details; decrease the block size and toggle "Low Block Resolution" off. When configuring block size, a typical target object is suggested to be covered by approx. 4-5 blocks. Each block should contain as large portion of the object as possible to decrease noise. Too many blocks covering the target object require substantially more computational power, while using very few blocks may result in mis-detections.

  • Detection Cooldown will start when an alarm occurs and no alarm will be triggered until it ends. Too short a Cooldown period might result in redundant triggers for longer lasting events. Whereas, too long a Cooldown period might not trigger for two separate events if they happen within a short interval.

  • Video analytics is performed on the 2D representation of the 3D world. Therefore, this needs to be considered during configuration. Detection areas must be drawn to cover all image areas where the target objects might appear.

  • For Direction Control, detection areas should be configured with all the environmental aspects in mind. All objects which potentially appear in the scene must be taken into consideration to avoid false alarms through occlusion or overlap.

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 Video analytics > Security monitoring, and then click the scenario you want to configure.
  4. Click the Areas tab.
  5. Define the area as required:
    1. Click and drag the area to move it to the location you want.
    2. Click and drag the white dots to adjust the shape and size of the area.
    3. (Optional) Add or remove areas.
      • Add areas ()
      • Remove the selected area or the selected point ()
        NOTE: When an area or point is selected, it is yellow.
  6. In the Area name field, rename the selected area.
  7. In the Tracking section, configure the following settings:
    Min. speed
    The minimum speed at which an object or person must travel to trigger an alert.
    NOTE: The velocity estimation is based on the configured perspective and depends on the accuracy of the configuration.
    Max. speed
    The maximum speed at which an object or person must travel to trigger an alert. When this maximum speed is exceeded, no alert is triggered. This option can be used to ignore fast moving objects, such as trains.
    Min travel distance
    The minimum distance that an object or person must travel to trigger an alert. Increasing this value can help minimize false alerts on small movement, such as trees moving in the wind.
    NOTE: The distance is estimated based on the configured perspective, which might result in inaccuracies.
  8. In the Alert section, configure the following settings:
    Min. time between alerts
    The minimum period between alerts that can be triggered for an area. Using a low value ensures that multiple alerts that are part of a single real-life event are captured. Using a high value might suppress valid alerts that occur quickly after one another.
    Alert activation time
    The period for which a detection must remain in an alarm region before it can trigger an alert. Using a high value filters out camera noise, but might result in missed alerts.
    Min. detection size
    Specifies how much of the detected object has to be active in the alarm region to trigger an alert. Using a low value might cause small motion patterns, such as animals to be detected. Using a high value can result in missed detections of people or objects.
    Detect all active blocks
    When this option is selected, active blocks anywhere in the defined area can trigger alerts.
    Detect only connected blocks
    When this option is selected, only active blocks that are adjacent to each other can trigger alerts. This option minimizes false alerts caused by scattered movement, such as camera noise.
  9. Click Apply.

Example

For an alert to be triggered, a person or object must do the following:
  • Travel at a speed between the configured Min. speed and Max. speed.
  • Travel at least the Min. travel distance.
  • Travel within the Max. deviation angle along the defined path.
  • Travel for at least the period specified for the Alert activation time.