BriefCam’s LPR Main Limitations
There are many factors that affect the performance of license plate recognition including license plate-specific challenges, camera types, camera placement, the speed of the vehicle and more.
Note the following when using BriefCam and LPR:
BriefCam’s license plate recognition is not designed to work in “plate only” scenarios, where the camera is set to capture only the license plate. This is because BriefCam only searches for license plates on vehicles – and in “plate only” scenarios, the actual vehicle is not fully visible.
The LPR will not work well in low light conditions (especially when the car’s lights are dazzling the camera), because the plate is usually not bright enough.
When dedicated strong IR illumination is used to strongly retro-reflect from the plate, the vehicle itself will usually be too dark to be detected.
License Plate-specific Challenges
Variations – Many regions in the world have their own type of license plates, resulting in multitudes of variations. The differences can include colors, fonts, size, logos, languages, patterns and layouts, all making the recognition harder and country specific.
Similarly shaped characters – Differentiating between 1 and I, 0 and O, O and Q, 8 and B, G and 6, etc. is very difficult, especially in “in the wild” surveillance scenarios, since the sets of characters have a similar shape and the visual quality is sometimes not good enough even for a human eye to detect.
Occlusions – A challenge specific for license plate recognition is that snow, dirt, mud and road grime may partially or fully obscure the plates.
License plate add-ons – Some plates have a plastic covering, which may prevent the license plate from reflecting light – or the plastic covering might reflect too much light and cause dazzling (saturation) of the camera, reducing the readability of the plate. In addition, the plates might have frames and screws, which may also interfere with the readability.
License plate types – Some plates are made from retro‐reflective material, which reflects light back to its source and makes the plate look bright. Other plates are made with a non‐reflective material, which disperses the light in multiple directions and the plate is not as bright as with retro-reflective material.
An accurate and robust license plate recognition system needs to be able to handle all of these challenges and more.
Camera Types
The type of cameras that are installed affect the performance of the license plate recognition.
Surveillance(CCTV) cameras, in general, produce less ideal footage for license plate recognition than mission specific cameras that were built specifically for LPR.
A camera with a built-in illuminator is recommended.
For 24-hour surveillance, the camera should include low light sensitivity and active illumination capabilities, for maintaining a fast exposure (shutter) rate to prevent motion blur.
Both visible light and near infrared cameras are supported, provided that the contrast between the characters and the plate’s background is high.
Camera Placement
For license plate recognition, a good recommendation when using BriefCam, is to place cameras in all entrances and exits, and the cameras should be positioned in such a way that the occlusions are minimal (and there is good separation between vehicles), with a vertical angle of less than 40 degrees.
In general, license plate recognition produces the best results when:
The cameras are positioned so that the angle of capture is at a minimum and the vehicles are seen as “head-on” as possible.
The camera is angled to avoid direct glare from headlights and taillights as well as from the trunk and hood (in the case of active illumination). Alternatively, the camera should have a wide dynamic range so it can clearly capture strong illumination and very low illumination in a single shot.
The lighting is sufficient, resulting in a quick shutter speed that produces a crisp image.
At nighttime, active illumination is needed.
The plate is clean and the lighting gives good contrast of the characters on the plate.
The focus of the camera is on the area where you expect license plates to appear.
The camera is steady to prevent image smearing.
The camera is not pointing in the direction of objects containing letters or numbers that could be mistakenly detected as license plates, such as billboards or bus stop benches with an advertisement.
Framerate Per Second (FPS)
A framerate is how often a camera produces frames and is usually measured in FPS or frames per second. In general, when possible, always set the video input to a contant framerate.
BriefCam works at a framerate of approximately 3 FPS (or lower). Due to the low-FPS processing, high-speed objects across the frame may not be detected.
Bitrate
The bitrate is the rate in seconds that bits are transmitted from one location to another. However, bitrate is not directly related to the number of pixels per frame (the resolution).
Bitrate can be used to control the quality of the video. On the one hand, the higher the bitrate, the better the quality. On the other hand, low bitrates save storage and transmission bandwidth. Two video streams of the same resolution can be configured to a different bitrate, where the higher the bitrate, the higher the quality, if all other parameters are identical.
Because the bitrate determines the quality of the video, the bitrate affects the accuracy of license plate recognition. The better the quality of the video, the better the accuracy of license plate recognition since more characters will be extracted accurately.
To achieve successful license plate recognition, higher bitrates are necessary in scenes that are more challenging, such as partial occlusions or dark scenes. When the camera’s field of view is very wide and objects look smaller, a higher resolution and bitrate contribute to the license plate recognition accuracy.
Higher bitrates may lead to more storage used.
Speed of Objects
The speed that a vehicle is traveling affects the accuracy of the license plate recognition. This is because the vehicle may become blurred as the speed increases, due to the way cameras capture the image. Another factor is that when an object is traveling faster, it appears in less frames, which also affects the accuracy, because the LPR algorithm has less frames to choose from, when selecting images of the plate to transcribe. Cameras should be configured in a way to generate sharp images with good contrast even though the vehicle is moving fast – and in a way that the license plate is visible for a long-enough time in the frame.
In general, if you have the appropriate camera, enough light and a good angle, BriefCam should be able to capture the license plate even if the vehicle is moving very fast. In addition, the LPR algorithm can even handle blurry images.