Page History

To configure License plate recognition (RR), do as follows:

1. Download Addon Add-on RR LPR from the website and install it.

   Info
   title Note
   To make the detection tool work under Windows Server operate on Windows Server 2012 R2, make sure to install the Media Foundation component.

   
   

2. Create the required detection object you need tool and select it (1). 
   Image Modified
3. If you require using need to use this detection tool for real-time number license plate recognition, set the corresponding parameter to Yes (1) (see Configuring real-time vehicle license plate recognition), set the corresponding parameter to Yes (2)..
4. To record metadata to the database, select If you need to enable recording of metadata, select Yes from the Record Objects objects tracking list  list (32).
5. If a the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream allows reducing reduces the load on the Server (3).
   Image Added

6. Select the Algorithm for detecting vehicle direction (4):

   1. By LP coordinates: if LP coordinates change position from top to bottom, the vehicle moves towards the camera. If LP coordinates change position from bottom to top, the vehicle moves away from the camera.
   2. By LP scale change: if LP scale increases, the vehicle moves towards the camera. If LP scale decreases, the vehicle moves away from the camera. 
7. In the corresponding fields, select Select your target country from the list one or more countries for LPR (5).
8. Select the processor for decoding video streams (6). 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 be done with Intel Quick Sync Video technology. Otherwise, the CPU resources will be used for decoding.
9. Set the number of frames processed per second by the detection tool (7). The value should be in the range [0,016; 100].
10. Set the minimum quality of LPR (8). The value should be in the range [0; 100]. The higher the minimum recognition quality, the fewer false detections will occur.

11. Select the processor for the detection tool: the CPU or one of NVIDIA GPUs (9) (see General Information on Configuring Detection).
    

    Note
    title Attention!
    It may take several minutes to launch the algorithm on NVIDIA GPU. You can use caching to speed up future launches (see Configuring the acceleration of GPU-based neuroanalytics).

    
    

12. From the Speed detection list, select the unit of measurement of vehicle speed (10).
13. Specify the speed detection area height and width (11, 12). The value should be in the range [0; 500].
14. If you need to search for the recognized LPs in the archive, set Yes for the corresponding parameter (13, see LPR search).

15. In the Event timeout field (14) specify the time interval in seconds between the initial LP recognition and event registration. The 0 value sets the event registration to the moment when the track disappears from FOV.
    

    Info
    title Note
    Skip this step with License plate recognition - Search in archive (RR).

    Image Added

16. By default, the analyzed frames are scaled Analyzed framed are scaled down to a specified resolution (215, 1920 pixels on the longer side). This is how it works:

    1. If the longer side of the source image exceeds the value specified in the Frame size change field, it is divided by two.

    2. If the resulting resolution falls below the specified value, it is this resolution will be used further.

    3. If the resulting resolution still exceeds the specified limitvalue, it is divided by two, etc.

       Info
       title Note
       For example, the source image resolution is 2048*1536, and the limit specified value is set to 1000. In this case, the source resolution will be divided halved two times (down to 512*384): , as after the first division, the number of pixels on the longer side exceeds the limit (1024 > 1000).

       
       

       Info
       title Note
       If detection is performed on a higher resolution stream and detection errors occur, it is recommended to reduce the compression.

       
       

17. Specify the maximum number of recognition threads (716). If the value is 0, the recognition process will occur in the same thread that starts it.
    

    Select the processor for the detection tool: the CPU or one of NVidia GPUs (9)

    Note
    title Attention!
    The cumulative value of this parameters across all LPR detection tools must should not exceed the number of CPU cores and is limited to 100.

18. Set minimum quality of ANPR (8). The higher the minimum recognition quality, the less false detections will occur.

19. .

    
    

    Note
    title Attention!
    It may take up to one minute to launch the algorithm on an NVIDIA GPU.

    Specify the time interval between the initial recognition and event registration in theTimeout field (10). Zero value sets the event registration to the moment when the track disappears from FOV.
    

    Info
    title Note
    Skip this step with License plate recognition - Search in archive (RR)Starting from DetectorPack 3.8.0.95 the Maximum number of threads parameter is not present.

    
    

20. You can configure an ANPR zone in FoVthe LPR area in the preview window. The zone area is resized by moving the anchor points Image Removedpoints Image Added. 
    Image RemovedImage Added

    Info
    title Note
    For your convenience, you can click the Image Removed button the Image Added button and configure the mask on a still frame / snapshot. To undo, click this button again.

    
    

    Info
    title Note
    Detection zone is displayed by default. You can click the Image Removed button the Image Added button to hide the zonearea. To undo, click this button again.

    
    

21. Click the Apply button.

Configuration of  of License plate recognition (RR) is now complete.