Skip to main content
All CollectionsMethodology & RequirementsRequirements
Requirements for ANPR Video Processing
Requirements for ANPR Video Processing

How to make your video suitable for GoodVision ANPR Video Processing?

Pavel Severa avatar
Written by Pavel Severa
Updated over a week ago

In GoodVision Video Insights, the license plate recognition feature (ANPR) is available only for traffic camera processings for videos that are stored in GoodVision Vault. As ANPR is an extension of the traffic data extraction process, all requirements for the standard processing must be satisfied, as well as further ANPR requirements specified in this document. Drone videos can neither fulfill the requirement of readable size of the license plate nor the right angle of the camera.

Naturally, with a higher resolution of your camera the quality, readability, and accuracy of your video processing boosts. So if you can, go for as high as 4K. However, we are aware that not everyone has the possibility to record in 4K resolution. There are several issues with ANPR camera setup that can impede its accuracy. In this article, we share the tips on how to improve your camera placement, setup, and scene description to increase the ANPR accuracy.

Requirements table

Viewpoint

Static

Camera distance

< 25m (depends on the resolution)

Resolution

ideally UHD/4K (3840 x 2160),

2K (2560 x 1440), Full HD (1920 x 1080) for videos recorded with camera closer than the max limit

Frame rate

FPS 25-30, 15 as a minimum

Pixel size

350 px for a traffic object, 100 px for a license plate for at least 10 frames

Camera angle

< 45°

Scene lighting

Other setup features

Automatic gain control (AGC), digital noise reduction (DNR), autofocus, backlight compensation shall be turned off

Camera distance

Logically, the closer the object is to the camera, the better chance you’ ll have to catch the license plate. That’ s why we advise to place a filter for ANRP analysis rather closer to the beginning of traffic scenes. The suggested distance of an object from a camera varies according to the video resolution, FPS, camera angle, light and other conditions but generally we recommend a maximum distance of around 25m, from which you can expect good results. The basic rule by ANPR is that if a human eye is able to read the license plate from the screen, the ANPR mechanism will most likely be able to read it too.

Video resolution

The Video Insights application will inform you about the number of suitable objects when creating the ANPR report. Suitable objects are vehicles that fulfill the minimal pixel size on the screen and thus enter the reading analysis.

The minimum pixel size of a vehicle to enter the ANPR process is set to 350 pixels, so that the actual license plate is at least 100-120 pixels wide for at least 10 frames. The lower the resolution, the bigger portion of the image the vehicle must take. But beware of zooming too close, otherwise the video will not be suitable for standard processing.

An example of how resolution affects the image and therefore LPR quality

FPS

Camera frame rate (FPS) is a very important parameter that limits the maximum speed of vehicles for reliable license plate recognition. See the table below that will help you choose the minimal FPS for a specific vehicle speed range.

Net Vehicle Speed (mph)

Frames Per Second (FPS)

10

10-15

30

15-25

60

30-40

Camera Angle

The only thing to keep in mind regarding the camera angle is that it should not exceed 45° in the vertical or horizontal direction - see the graphics below. Anything above 45° is complicating the detection.

Your camera shall have direct visibility of the vehicles and their license plates at the point of the scene, where you need to recognize it, so try to avoid the camera positioning where the vehicles overlap each other, like a direct angle.

Other conditions

The clarity of the license plate depends also on natural conditions of the monitored area, like day/night or actual weather as well as on the camera settings. Try to check possible problems like blur, fog, light under/overexposure etc. and optimize the camera recording options. For example, features like the Automatic gain control (AGC), digital noise reduction (DNR), autofocus, and backlight compensation should be rather disabled while enabling the ANPR camera setup.

And here is how it should and shouldn't look like in practice:

NOTE: Example of a video with a motion blur due to too long shutter speed.

NOTE: Both of these scenes may look suitable for ANPR recognition, however, not both of them are good for Standard Processing.

In the first scene the camera is placed too low which may cause overlapping of the vehicles. The limited view can cause that the vehicle trajectories will not be captured correctly and the licence plate number not properly assigned.

The second scene is ideal for ANPR, having high resolution of 4K, good vertical and horizontal angle and no motion blur.

Read more about ANPR feature in GoodVision here.

If you are still not sure about the usability of your footage contact us!

Did this answer your question?