Introduction #
With its powerful AI Image Analysis, Synology Deep Video Analytics (DVA) can instantly calculate large amounts of object attributes, filter out environmental interference, and deliver accurate detection results. Backed with Smart Tag technology and a comprehensive management interface, it allows users to take control of events with ease and efficiency.
Among the supported algorithms, License Plate Recognition specializes in detecting vehicle license plates when vehicles have entered a specific area. To accommodate different scenarios and security levels, you can track and customize your own trigger times.
For you to achieve optimal precision, this guide aims to introduce the key factors of setting up License Plate Recognition in People and Vehicle Detection tasks. For best results, please follow the listed points as closely as possible.
System requirements #
- Surveillance Station version 9.0.0 or later.
- Synology’s Deep Learning NVR. (Synology Deep Video Analytics—also known as DVA—installed by default).
Note:
- No additional licenses required for People and Vehicle detection.
Quick Camera Installation #
Select appropriate camera #
Stream quality: Ranging from 1920×1080 @20FPS to 3840×2160 (4K)
Sunshield: (Optional) Added to outdoor cameras to avoid direct sunlight on the lens
Check installation environment #
Minimum illumination: 300 lux
Mounting height and angle #
Installation height: 3 – 10 meters
Camera tilt angle: 15 – 30 degrees
Horizontal angle: 25 degrees
Camera roll angle: 25 degrees
Detection area: 7 meters – 20 meters
Position the Camera #
When you mount the camera for License Plate Detection, it is important to get a good, clear view of the area of interest so the plate can be detected consistently. This ensures accurate reading and minimizes false detection. The following are methods to best position your camera:
- Avoid objects blocking the camera’s field of view such as pillars, barriers, fences, gates, trees, etc.
- Avoid irrelevant moving objects such as people or traffic.
- Mount the camera as close as possible to the area of interest.
- Adjust the camera angles for optimal detection.
- Use the camera’s optical zoom, if applicable.
- Mount the camera so the license plate appears from the top of the image (or bottom if traffic is driving away from the camera) instead of from the right or left side. In this way, you make sure that the recognition process of the license plate only starts when the whole plate is in the view.
Ensure Detection Accuracy #
A suitable camera placement and environment can ensure detection accuracy. The following situations can affect detection by the AI:
- Light shining directly into the camera’s lens may leave streaks in the images or cause overexposure, affecting the picture quality.
- The camera installed in areas where drastic changes in lighting can happen can lead to inconsistent picture quality.
- Overexposed or underexposed license plates images can impede recognition by the AI.
- Backgrounds with yellowing lighting can impede recognition by the AI; white lighting is recommended.
- Vehicle moving too fast might cause captured license plates images to blur.
- Changes in the camera’s field of view might affect the video analytic results (e.g., changes in focus or zoom level).
- Weather sometimes affects the clarity of outdoor cameras. Rain and snow, changes of shadows, or differences between day and night can have an impact on detection and recognition.
- An unstable network connection might lead to incomplete or corrupt images. Wired connections are highly recommended.
- Dust, insects, or other stains can block the lens. Keep the lenses clean so that a clear image can be taken.
- Slow shutter speed can cause motion blur.
Detection accuracy factors #
| Vehicle | Physical Surroundings | Camera |
|---|---|---|
|
|
|
Image Quality #
A bad image, like motion blur, will result in lower recognition. Make sure to check your settings to optimize the image quality.
Stroke width #
A stroke width that is too wide may result in unrecognizable license plates or inaccurate results. To ensure accurate recognition, the minimum character height must be 30 pixels and the minimum plate width must be 150 pixels.
Minimum frame rate #
A frame rate that is too low may result in unrecognizable license plates or inaccurate results.
To ensure accurate recognition, the minimum frame rate when used with a DVA3221 must be at least above 20 FPS.
Vehicle speed #
The speed of the vehicle may affect whether the license plate can be identified correctly.
If you only need to identify license plates when the vehicle is not in motion, such as at parking lot entrances and exits, we recommend using the DVA1622.
To identify the license plate number of a moving vehicle, we recommend using the DVA3221. When paired with the DVA3221, license plates can be detected for vehicles moving at speeds up to 40 km/h.
Supported Regions #
We support all license plates that contain numeric or alphanumeric characters. Select the following region to get an accurate reading.
- Australia
- Belgium
- Czech
- Denmark
- Estonia
- France
- Germany
- Greece
- Hungary
- Italy
- Japan
- Lithuania
- Luxembourg
- Netherlands
- New Zealand
- Poland
- Portugal
- Romania
- Slovakia
- Slovenia
- Switzerland
- Spain
- Taiwan
- Thailand
- Türkiye
- United Kingdom
- United States
- Vietnam
Camera Settings #
| Resolution | 1080 pixels or higher |
| Capture distance | 7 – 20m |
| Mounting height | 3 – 10m |
| Camera orientation – Tilt | 15º – 30º |
| Camera orientation – Horizontal | 25º |
| Camera orientation – Roll | 25º |
| Minimum frame rate | 20 FPS |
| Maximum acceptable traffic speed for successful recognition | DVA3221: 40 km/hr |
| DVA1622: stationary | |
| Maximum number of license plates that can be recognized in one frame | DVA3221: 4 |
| DVA1622: 1 | |
| Minimum character height | 30 pixels |
| Minimum plate width | 150 pixels |
| Minimum number of plate characters | 4 |
| Maximum number of plate characters | 12 |
| Database number | 10,000 |
| Match tolerance | 2 |
| Two-line plate detection | Only supported for Vietnam, Thailand and Japan |
Configure Software Settings #
Once your cameras are mounted successfully, you can configure software settings for the DVA to suit your requirements. This chapter covers the essential settings for the License Plate Recognition.
Select people & vehicle detection #
To use the License Plate Recognition function, select People & Vehicle Detection as your task type.
Select a stream profile #
For optimal detection accuracy, select a stream profile with a resolution of between 1920×1080 @20FPS and 3840×2160 (4K). Stream profiles are set by the Intelligent Video Analytics Recording settings of the paired camera. To edit stream profiles, go to IP Camera and select the camera you want to configure. Then click Edit > Edit > Recording > Stream > Intelligent Video Analytics Recording to set the stream profile.
Note:
- To edit specific stream profile settings, go to IP Camera > select a camera > Edit > Edit > Video & Audio Format > Video.
Enable the license plate recognition function #
In the Configure detection properties page, select License plate recognition to enable the relevant function.
Select the specific region to optimize the recognition accuracy.
If Japan is selected in the Region setting, enabling Limit recognition to the numeric area in the lower section can improve accuracy by narrowing the recognition area.
Add license plates to the license plate database. Select Add Allow or Block icons to detection results to automatically compare license plates in the database with detection results and matches with Allow or Block.
Manage the License Plate Database #
You can manage your license plate database by going to Recording App > License Plate > More > Manage License Plate Database or in the settings of the People and Vehicle task.
The database can contain up to a total of 10,000 user profiles and the license plate can include 1 to 64 Unicode characters.
To create a license plate profile, click Add. Fill in the license plate numbers, choose Allowed or Block, and add a description.
Manage Detection Results #
Go to the Recording App > License Plate to manage the license plate results.
If there is a license plate that was detected incorrectly, right-click on the result or click on the Menu icon > Edit license plate to edit the license plate.
Alert Settings #
If you want to receive alarms for Unknown/Allow/Block license plates, go to Monitor Center > Alert Panel > Alert settings.
Select the device and tick the box to receive alerts for Unknown, Allowed, or Blocked license plates detected.
You can find the following alert information in the alert panel:
- Date and time
- License plate number
- Description
- Status
Export Reports #
If you need to manage or analyze the detected vehicles, go to the Recording App > License Plate > More > License Plate Report.
Filter your results and export the license plate report.
