Vehicle Motion Detection

The motion detection feature allows you to capture vehicles which may have no plate or a badly damaged plate.

The configuration of the motion detection engine requires a certain amount of fine tuning to get it working at its optimum for the specific road being monitored, but once setup correctly it should detect every vehicle passing through the field of view. Due to the nature of motion detection employed, it is very resistant to false triggering from, for example, moving shadows and multiple triggers from long vehicles.

To use this feature, you must first enable Transmit Blank Plates from the current lane’s settings, and you must not be using Triggered ANPR.

The motion detection works independently for each ANPR camera (it cannot be configured on surveillance cameras), so each camera can have its own unique settings, tuned to that camera's specific view of the road it is monitoring.

Traditional motion detection works by comparing sections of a video, looking for changes between consecutive frames. The motion detection method used here works by looking for horizontal and vertical lines, which are very distinctive for vehicles, and see how these change from frame to frame.

The "motion detection area" is defined by the green rectangle shown in the video window. The four corners of the rectangle can be dragged around to cover the required area to use for motion detection.

The white gridlines divide up the motion detection area into smaller boxes. The number of boxes can be configured by adjusting the Number of rows and Number of columns values. For each frame, the motion detection algorithm calculates the number of horizontal and vertical lines present within each box, which are shown as red and green lines within the video window.

Once the configured criteria have been reached, the current frame is shown in the smaller "motion detection result" window. If the ANPR engine fails to detect a plate, for whatever reason, during a motion-detected trigger period this is the image that will be transmitted as a "blank plate".

Configuration Criteria Settings:

No. Boxes Hit

Specifies the number of cells within the main box that must either contain lines or show difference between frames before the motion event is triggered. The maximum value allowed is defined as the total number of white boxes within the main green rectangle.

No. Lines Per Box

How many lines each box must contain before being considered to contain lines. This helps to ignore any static lines in the image from, for example, road markings.

Hold Trigger for n Frames

Once a motion event is triggered, this control specifies for how long, in frames, the trigger lasts. This feature will stop multiple triggers occurring from the front/rear of the vehicle (depending on traffic direction).

Number of Rows

Number of rows in the main box.

Number of Columns

Number of columns in the main box.

Priorities

This control set whether the horizontal or vertical lines in each cell are used to calculate the "No. Boxes Hit". This helps to differentiate between the front and back edges of a vehicle. For example, consider vehicles moving from the top to the bottom of the field of view: The front of the vehicle will have many more vertical lines (from radiator grill, etc) than the back edge. If a long vehicle passes through, the front will trigger the motion event. As the vehicle passes, the rear will not trigger an event because it has fewer vertical lines.

Look For

Tells the motion detection algorithm whether to count the number of cells that currently contain lines or whether to count the number of cells that changed between consecutive frames.