License Plate Detection Events
Flussonic Watcher can detect license plates and recognize license plates on the video transmitted by an IP camera including non-standard formats. This functionality is known as ANPR (automatic number plate recognition) or LPR (license plate recognition).
Flussonic Watcher does the following:
Creates events of license plate detection. Video comes from IP cameras to a streamer (in cluster mode) or to the managing server (in single mode), where the license plate recognition takes place.
Provides the Watcher UI for viewing plate detection events. You can view registered events and watch the recorded video of each event.
Provides the API for integration with external services.
License plate recognition is available for the following countries:
- All EU (European Union) countries
To start detecting license plates:
Prepare hardware and software for the Flussonic server that will carry out license plate recognition — see Video analytics module.
Check the video image parameters for compliance with the recommendations (see below).
Turn on and configure the license plates recognition.
On this page:
Recommended video image parameters for LPR
A general requirement for a video image for LPR is the ability to read the license plate with human eyes. In other words, if you do not perceive the license plate in the video, then Watcher will not be able to recognize it either.
Stable LPR is guaranteed with the following video image characteristics:
- At least HD resolution (1280 x 720). If the frame has larger resolution, it will be reduced to 720p before feeding to the analytics module. Also, if camera has several streams, the closest to 720p will be used for analytics purposes.
- The size of the license plate in the image at least 100 x 20 pixels at 720p. If the frame has larger resolution, the LP size should be proportionally larger.
- Good illumination.
- Colored image is better than black-and-white.
- Any camera view angle.
However, if your video image does not meet these guidelines or even if your country is not supported yet, you can check to see if recognition will work. If the LPR quality turns out to be unsatisfactory, we may consider the module modification to suit your conditions. Please contact our technical support team by following these instructions. Technical support team member will request the necessary information and will let you know if the improvements are possible and when we will implement them.
Please note that if your country is already on the list, then access to video stream(s) where the recognition quality does not meet expectations is enough. If you want us to support the license plates recognition for a new country, then most likely you will be asked to provide access to two types of streams:
- The camera is aimed at the license plate at a right angle (90°)
- The camera is aimed at the license plate at an arbitrary angle
|Example right angle|
|Example arbitrary angle|
Technical support team member will provide a detailed info at your request.
Setting up LPR
Enabling video analytics on the server
By default, the analytics functions are disabled on all servers in your system. To enable analytics:
- Go to Health and click the streamer name.
Setting up LPR on the camera
To turn on license plate detection and recognition for a camera:
In the Watcher UI, go to Cameras. Find the camera in the list and open its settings by clicking the icon in the upper right corner of the player.
Check the Enable recognition box.
Select Recognize license plates in the drop-down list that appears when you check the box.
Select the period to store precise thumbnails for, if necessary. Please refer to Camera settings for details on precise thumbnails.
The recognition settings may not be available if a non-adjustable preset is selected. In this case, select or create the preset with the settings you need.
By default, the recognition system searches for license plates over all the camera field of view. You can select specific polygonal area(s) to detect license plates in by clicking Set up the detection zone. This settings may help you to reduce false detections. The areas are set in a dialog:
There are controls in the dialog header: buttons for selecting already created areas, as well as buttons for creating and deleting areas.
You can drag-and-drop the created area to the desired position on the frame and move the vertexes. If you want to delete an area, select it and click the trash can icon. Click OK when all areas are set.
Make sure that your areas are convex and do not intersect each other. Any area should cover at least quarter of the frame. You will see a warning if any of the requirements is not fulfilled while the OK button will be disabled until you make fixes according to the remarks.
Areas are set individually for each camera, even if you select a non-configurable preset.
Save the camera settings.
Now Flussonic Watcher will recognize license plates that appear in the frame of this camera, and mark the time when the vehicle entered and left the scene.
Viewing LPR events in Watcher
Flussonic Watcher creates events of two types:
- enter – a license plate appeared in the field of view of a camera
- leave – a license plate left the field of view.
To see detected license plates for a camera:
- In the Watcher UI, go to Events - License plates. The list of all events opens.
You can use filter to find specific events:
- In Camera, enter the camera name.
- In From and To, select the date and time of beginning and end of the period when events were detected.
- In Search, type the license plate text (numbers and letters).
- From the Organization list, select the Organization that includes cameras events from which you want to see.
- To delete the specified search criteria, click Clear Filters.
The list of events is filtered as you enter search parameters.
Click the event to view its recording. The player will appear on the right, playback position will be set to the recording. You can control playback just like in the usual player.
Use controls in the header to page events or switch between screenshot and list view.
See also Events.