Versions Compared

Old Version 8

changes.mady.by.user Evgeniya Kononova

Saved on

compared with

New Version Current

changes.mady.by.user Alena Kniazeva

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Note
titleAttention!

If you want to use the computing resources of the NVIDIA GPU to improve license plate recognition, select the required option from the Use GPU drop-down list on the settings panel

Configure IV module as follows:

...

of the LPR channel

...

titleAttention!

 object (see Selecting a device for license plate recognition).

The startup (initialization) time of the algorithm of license plate recognition

...

on the NVIDIA GPU can take

...

approximately one minute. No

...

license plate recognition events

...

are received until

...

initialization is complete.

To set up the IV module:

  1. Go to the settings of the IV module object created on the basis of the LPR channel object.
    Image Added
  2. From Select the LPR accuracy in the Accuracy drop-down list (2). The following options are available, select the accuracy of the license plate recognition:
    1. Maximum—enables maximum recognition accuracy, but it causes great creates a high load on the CPU and/or GPU load.  
    2. High—enables high recognition accuracy, it requires less fewer computing resources than for maximum accuracy.
    3. Fast—enables high recognition speed, but the recognition accuracy becomes worseis reduced.
  3. Select the computing resources use mode in the Strategy drop-down list(3). The following options are availableFrom the Strategy drop-down list, select the usage mode of computing resources:
    1. Process—mild mode: , no more than 1 one core for 1 per license plate is used.
    2. System—default System—the default mode: , all available computing cores are in use;.
    3. Core—strict mode: 1 , one core per stream .
  4. From the Platform drop-down list (4), select the device on which the module will operate:
    1. Default—CPU resources are used for computing.
    2. TensorRT—NVIDIA GPU resources are used for computing.
    3. CV22, NCNN, HISI, Qualcomm, TFLite, OpenVino—other device resources are used for computing, if available. These options apply to platforms other than x86/x64.
    1. is used.
  6. In the Interval field (5), specify the minimum time interval in milliseconds that lasts between frames frame processing (i.e. that is, all frames within this interval will not be processed). The range of values is 0-999, ; the default value is 0.

  7. Select From the Profile drop-down list, select the profile of country license plates that are to must be recognized in the Profile drop-down list(6). 

    Note
    titleAttention!

    The profile of country license plates should must match the selected country for license plate recognition (see Selecting the country and license plate recognition SDK).

    The following options are available:

    • 0—Common. This Select this profile should be selected if you select By default country is selected.

    • 3, 6, and 9—for more information, see The IV module functionality.

      Info
      titleNote

      The 9

       profile enables recognizing correctly

      profile enables the correct recognition of the USA license plates with vertical letters on the plates. It can also be recommended to be in use when maximum recognition accuracy is needed if there is no high load on hardware.  

      Greater

      A higher profile number enables more accurate

      LPR comparing

      license plate recognition compared to the solution with

      smaller

      a lower number, but it is more demanding

      to

      on computing resources.

  8. Click the Apply button (7).

Configuration of the IV module is completedcomplete.