Documentation for Axxon One 2.0. Documentation for other versions of Axxon One is available too.

Previous page Activating the license for the License plate recognition IV in Linux OS  License plate recognition RR and Vehicle recognition RR Next page

Hardware requirements for neural analytics operation

Hardware requirements for the License plate recognition IV

Video stream and scene requirements for the License plate recognition IV and its sub-detectors

Image requirements for the License plate recognition IV and its sub-detectors

Activating the license for the License plate recognition IV in Windows OS

Activating the license for the License plate recognition IV in Linux OS

Checking in lists of LPs

Examples of macros used when working with lists of license plates

Attention!

For the License plate recognition IV to work, you must activate the license (see Activating the license for the License plate recognition IV in Windows OS, Activating the license for the License plate recognition IV in Linux OS).

To configure the License plate recognition IV detector, do the following:

  1. Go to the Detectors tab.
  2. Below the required camera, click Create… → Category: Vehicle → License plate recognition IV.

By default, the detector is enabled and set to recognize vehicle license plates.

If necessary, you can change the detector parameters. The list of parameters is given in the table:

ParameterValueDescription
Object features
Check in listsYesThe parameter is disabled by default. If you want to use this detector to check in lists of vehicle license plates, select the Yes value (see Checking in lists of LPs)
No
Record objects trackingYesThe metadata of the video stream is recorded to the database by default. To disable the parameter, select the No value
No
Video streamMain streamIf the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream reduces the load on the server
Second stream
Other
EnableYesThe detector is enabled by default. To disable the detector, select the No value
No
NameLicense plate recognition IVEnter the detector name or leave the default name
Decoder modeAutoSelect a processing resource for decoding video streams. When you select a GPU, a stand-alone graphics card takes priority (when decoding with Nvidia NVDEC chips). If there is no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding
CPU
GPU
HuaweiNPU
TypeLicense plate recognition IVName of the detector type (non-editable field)
Advanced settings
Frame size change1920

The analyzed frames are scaled down to a specified resolution (1920 pixels on the longer side) by default. The following algorithm is used:

  • If the longer side of the source image exceeds the value specified in the Frame size change parameter, it is divided by two.
  • If the resulting resolution falls below the specified value, the algorithm stops and this resolution will be used further.
  • If the resulting resolution still exceeds the specified value, it is divided by two until it is less than the specified resolution.

Note

For example, the source image resolution is 2048*1536, and the specified value is set to 1000. In this case, the source resolution will be halved two times (512*384), as after the first division, the number of pixels on the longer side exceeds the specified value (1024 > 1000). If detection is performed on a higher resolution stream and detection errors occur, we recommend reducing the compression.

Initiate event in (sec)1Specify the time in seconds after which an event must be generated after recognizing a license plate in the frame. The value must be in the range [0, 3600]. If the value is 0, an event will be generated after the track with a license plate is lost
Maximal number of characters in LP10Specify the maximum number of characters in the license plate. The value must be in the range [1, 20]
Minimal number of characters in LP5Specify the minimum number of characters in the license plate. The value must be in the range [1, 20]
Minimum recognition quality, in %80Specify the minimum quality of license plates recognition as a percentage. The higher the minimum recognition quality, the fewer false events. The value must be in the range [0, 100]
Track retention time (sec)3

Specify the time in seconds after which the vehicle track is considered lost. The value must be in the range [0, 3600].

Note

You can use this parameter to avoid double events that can occur, for example, when a license plate is recognized when it appears in the frame, then it is overlapped by a visual obstacle and then recognized by the detector again. If you specify the timeout longer than the time of possible overlapping of the license plate in the frame, the detector will generate an event only once.

Basic settings
Algorithm for detecting vehicle directionBy LP coordinates

The By LP coordinates algorithm is used by default. It works as follows: if the coordinates of the vehicle license plate shift from top to bottom (the vehicle moves towards the camera) and if the coordinates of the vehicle license plate shift from bottom to top (the vehicle moves away from the camera).
Select the By LP scale change parameter if in the Surveillance window, the scale of the vehicle license plate increases (the vehicle moves towards the camera) and if the scale of the vehicle license plate decreases (the vehicle moves away from the camera)

By LP scale change
Maximum LP width10

Specify the maximum and minimum width of the license plate as a percentage according to the actual size of the license plate in the frame. The value must be in the range [0, 100].

Attention!

  • Specified values must exclude omissions in license plate recognition, that is the values must not be smaller than the real size of the license plate in the frame. Otherwise, the license plates won't be recognized.
  • The Minimum LP width parameter affects the CPU load: the higher the value, the lower the load.
  • Reducing the difference between the maximum and minimum width reduces the CPU load.
Minimum LP width1
Processing unit




CPU

Select a processor for the detector operation (see Selecting Nvidia GPU when configuring detectors).

Attention!

  • It can take several minutes to launch the algorithm on NVIDIA GPU.
  • If you have multiple graphics cards in your system, you can assign a specific NVIDIA GPU value to each License plate recognition IV detector.
Nvidia GPU 0
Nvidia GPU 1
Nvidia GPU 2
Nvidia GPU 3
Country selection
Country name
  • Australia, high load, high recognition accuracy
  • Australia, medium load, medium recognition accuracy
  • Austria, high load, high recognition accuracy
  • Austria, medium load, medium recognition accuracy
  • Bangladesh, high load, high recognition accuracy
  • Bangladesh, medium load, medium recognition accuracy
  • Belarus, high load, high recognition accuracy
  • Belarus, medium load, medium recognition accuracy
  • Belgium, high load, high recognition accuracy
  • Belgium, medium load, medium recognition accuracy
  • Brazil, high load, high recognition accuracy
  • Brazil, medium load, medium recognition accuracy
  • Canada, high load, high recognition accuracy
  • Canada, not supported
  • Canada, medium load, medium recognition accuracy
  • China, high load, high recognition accuracy
  • China, medium load, medium recognition accuracy
  • Costa Rica, high load, high recognition accuracy
  • Costa Rica, medium load, medium recognition accuracy
  • Czech Republic, high load, high recognition accuracy
  • Czech Republic, medium load, medium recognition accuracy
  • Dubai, high load, high recognition accuracy
  • Dubai, medium load, medium recognition accuracy
  • Egypt, high load, high recognition accuracy
  • Egypt, medium load, medium recognition accuracy
  • European Union, high load, high recognition accuracy
  • European Union, not supported
  • European Union, medium load, medium recognition accuracy
  • Finland, high load, high recognition accuracy
  • Finland, medium load, medium recognition accuracy
  • France, high load, high recognition accuracy
  • France, medium load, medium recognition accuracy
  • Germany, high load, high recognition accuracy
  • Germany, medium load, medium recognition accuracy
  • Hong Kong, high load, high recognition accuracy
  • Hong Kong, medium load, medium recognition accuracy
  • India, high load, high recognition accuracy
  • India, medium load, medium recognition accuracy
  • Indonesia, high load, high recognition accuracy
  • Indonesia, medium load, medium recognition accuracy
  • Iraq, high load, high recognition accuracy
  • Iraq, medium load, medium recognition accuracy
  • Israel, high load, high recognition accuracy
  • Israel, medium load, medium recognition accuracy
  • Italy, high load, high recognition accuracy
  • Italy, medium load, medium recognition accuracy
  • Japan, high load, high recognition accuracy
  • Japan, medium load, medium recognition accuracy
  • K.U.B.R., high load, high recognition accuracy (Kazakhstan, Ukraine, Belarus, Russia)
  • K.U.B.R., medium load, medium recognition accuracy (Kazakhstan, Ukraine, Belarus, Russia)
  • Kazakhstan, high load, high recognition accuracy
  • Kazakhstan, medium load, medium recognition accuracy
  • Kuwait, high load, high recognition accuracy
  • Kuwait, medium load, medium recognition accuracy
  • Luxembourg, high load, high recognition accuracy
  • Luxembourg, medium load, medium recognition accuracy

  • Macau, high load, high recognition accuracy

  • Macau, medium load, medium recognition accuracy

  • Malaysia, Singapore, high load, high recognition accuracy
  • Malaysia, Singapore, medium load, medium recognition accuracy
  • Mexico, high load, high recognition accuracy
  • Mexico, medium load, medium recognition accuracy
  • Middle East, high load, high recognition accuracy (Bahrain, Egypt, Iraq, Jordan, Kuwait, Lebanon, Oman, Qatar, Saudi Arabia, Syria, United Arab Emirates, Yemen)
  • Middle East, medium load, medium recognition accuracy (Bahrain, Egypt, Iraq, Jordan, Kuwait, Lebanon, Oman, Qatar, Saudi Arabia, Syria, United Arab Emirates, Yemen)
  • Monaco, high load, high recognition accuracy
  • Monaco, medium load, medium recognition accuracy
  • Mongolia, high load, high recognition accuracy
  • Mongolia, medium load, medium recognition accuracy
  • Netherlands, high load, high recognition accuracy
  • Netherlands, medium load, medium recognition accuracy
  • North America, high load, high recognition accuracy (Canada, Mexico, United States)
  • North America, medium load, medium recognition accuracy (Canada, Mexico, United States)
  • Pakistan, high load, high recognition accuracy
  • Pakistan, medium load, medium recognition accuracy
  • Poland, high load, high recognition accuracy
  • Poland, medium load, medium recognition accuracy
  • Portugal, high load, high recognition accuracy
  • Portugal, medium load, medium recognition accuracy
  • Russia, high load, high recognition accuracy
  • Russia, not supported
  • Russia, medium load, medium recognition accuracy
  • Saudi Arabia, high load, high recognition accuracy
  • Saudi Arabia, medium load, medium recognition accuracy
  • Singapore, high load, high recognition accuracy
  • Singapore, medium load, medium recognition accuracy
  • Slovenia, high load, high recognition accuracy
  • Slovenia, medium load, medium recognition accuracy
  • South Africa, high load, high recognition accuracy
  • South Africa, not supported
  • South Africa, medium load, medium recognition accuracy
  • South Korea, high load, high recognition accuracy
  • South Korea, medium load, medium recognition accuracy
  • Spain, high load, high recognition accuracy
  • Spain, medium load, medium recognition accuracy
  • Sri Lanka, not supported
  • Sri Lanka, medium load, medium recognition accuracy
  • Switzerland, high load, high recognition accuracy
  • Switzerland, medium load, medium recognition accuracy
  • Taiwan, high load, high recognition accuracy
  • Taiwan, not supported
  • Taiwan, medium load, medium recognition accuracy
  • Thailand, high load, high recognition accuracy
  • Thailand, medium load, medium recognition accuracy
  • Turkey, high load, high recognition accuracy
  • Turkey, medium load, medium recognition accuracy
  • Ukraine, high load, high recognition accuracy
  • Ukraine, medium load, medium recognition accuracy
  • United Kingdom, high load, high recognition accuracy
  • United Kingdom, medium load, medium recognition accuracy
  • United States, high load, high recognition accuracy
  • United States, not supported
  • United States, medium load, medium recognition accuracy
  • Uzbekistan, high load, high recognition accuracy
  • Uzbekistan, medium load, medium recognition accuracy
  • Vietnam, high load, high recognition accuracy
  • Vietnam, medium load, medium recognition accuracy

Select from the list the country whose license plates you want to recognize and select the recognition accuracy:

    1. High load, high recognition—provides maximum recognition accuracy, but creates a high load on the CPU and/or graphics processing unit (GPU).
    2. Medium load, medium recognition—provides high recognition accuracy, requires less computing resources than at maximum accuracy.
    3. Low load, low recognition—provides the fastest recognition speed, while lowering recognition accuracy

In the window, specify the area in which license plate detection and recognition will be performed. You can adjust the area by moving the anchor points .

Note

  • For convenience of configuration, you can "freeze" the frame. Click the  button. To cancel the action, click this button again.
  • The detection area is displayed by default. To hide it, click the  button. To cancel the action, click this button again.

To save the parameters of the detector, click the Apply  button. To cancel the changes, click the Cancel  button.

Configuration of the License plate recognition IV is complete. If necessary, you can create and configure the necessary sub-detectors on the basis of the License plate recognition IV (see Standard sub-detectors).

  • No labels