Documentation for Axxon Next 4.5.0. Documentation for other versions of Axxon Next is available too.
To configure License plate recognition (IV), do as follows:
- Download Addon IV LPR from the website and install it.
Submit the MAC address of the Server intended for detection tool operation to Axxon's tech support.
The detection tool will not operate on a Server having a different MAC address.
- Copy an IntelliVision license into C:\Program Files\Common Files\AxxonSoft\DetectorPack\IntelliVisionLPRlicense.txt.
- Select the License plate recognition (IV) object (1).
If you require using this detection tool for real-time number plate recognition (see Configuring online Vehicle License Plate recognition), set the corresponding parameter to Yes (2).
- If you need to enable recording of metadata, select Yes from the Record Objects tracking list (3).
- If a camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream allows reducing the load on the Server (4).
Select the country from the list (1).
Several profiles are provided for India, USA, Russia, Taiwan, Australia and African countries, differing by recognition parameters and hardware requirements.
To recognize US license plates with vertical orientation of characters, a profile with higher accuracy of recognition is recommended.
The list of supported countries is given in the manufacturer's specifications.
- Select a processing resource for decoding video streams (2). When you select a GPU, a stand-alone graphics card takes priority (when decoding with NVidia NVDEC chips). If there's no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding.
- Specify the minimum number of milliseconds between frames during recognition (3).
Analyzed framed are scaled down to a specified resolution (4, 1920 pixels on the longer side). This is how it works:
If the longer side of the source image exceeds the value specified in the Frame size change field, it is divided by two.
If the resulting resolution falls below the specified value, it is used further.
If the resulting resolution still exceeds the specified limit, it is divided by two, etc.
For example, the source image resolution is 2048 * 1536, and the limit is set to 1000.
In this case, the source resolution will be divided two times (down to 512 * 384): after the first division, the number of pixels on the longer side exceeds the limit (1024 > 1000).
- Specify the maximum number of processor cores available for the detector. '0' means all cores (5).
- Set the maximum and minimum width of the vehicle number plate as a percentage of the FoV width (6, 7).
- Set minimum quality of ANPR (8). The higher the minimum recognition quality, the less false detections will occur.
- By default, CPU resources are solely used for recognition. If you want to apply GPU computing resources to increase the recognition performance, select GPU in the Processor Type field (9).
- Specify the maximum and minimum number of digits in the number (1, 2).
- Select recognition accuracy (3):
Maximum: offers maximum recognition accuracy at the expense of higher CPU / GPU load.
High: offers acceptable recognition accuracy for less CPU / GPU effort.
Fast: offers fastest recognition speed at the expense of accuracy.
Specify the time interval between the initial recognition and event registration in the Timeout field (4). Zero value sets the event registration to the moment when the track disappears from FOV.
- In the Tracker timeout field, enter a time period in seconds. This is the time before detection starts again after a number plate is recognized (5).
You can configure an ANPR zone in FoV. The zone is resized by moving the anchor points.
For your convenience, you can click thebutton and configure the mask on a still frame / snapshot. To undo, click this button again.
Detection zone is displayed by default. You can click thebutton to hide the zone. To undo, click this button again.
- Click the Apply button.
Configuration of License plate recognition (IV) is now complete.