Go to documentation repository
Documentation for Axxon One 2.0. Documentation for other versions of Axxon One is available too.
Hardware requirements for neural analytics operation
Hardware requirements for the License plate recognition VT
Video stream and scene requirements for the License plate recognition VT and its sub-detectors
Image requirements for the License plate recognition VT and its sub-detectors
Optimizing the operation of the License plate recognition VT on GPU in Windows OS
Optimizing the operation of the License plate recognition VT on GPU in Linux OS
Licensing of the software module for the License plate recognition VT in Windows OS
Licensing of the software module for the License plate recognition VT in Linux OS
Examples of macros used when working with lists of license plates
To configure the License plate recognition VT detector, do the following:
- Go to the Detection Tools tab.
- Below the required camera, click Create… → Category: Vehicle → License plate recognition VT.
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:
Parameter | Value | Description |
---|---|---|
Object features | ||
Check in lists | Yes | The 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 tracking | Yes | The metadata of the video stream is recorded to the database by default. To disable the parameter, select the No value |
No | ||
Video stream | Main stream | If the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream reduces the load on the Server |
Other | ||
Enable | Yes | The detector is enabled by default. To disable the detector, select the No value |
No | ||
Name | License plate recognition VT | Enter the detector name or leave the default name |
Decoder mode | Auto | Select 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 | ||
Direction of movement | Both | By default, an event is created when a vehicle moves in both directions. If it is necessary to create an event when a vehicle moves only away from the camera, select Outgoing; if it is necessary to create an event when a vehicle moves only towards the camera, select Incoming |
Outgoing | ||
Incoming | ||
Period of ignoring repeated recognitions | 0 | Specify the period in seconds during which re-recognized license plates will be ignored. The value must be in the range [0, 86400] |
Type | License plate recognition VT | Name of the detector type (non-editable field) |
Advanced SDK settings | ||
VodiCTL_VPW_DYNAMIC_ENABLE | Yes | By default, the license plate recognition dynamics is enabled, that is, tracking is enabled, and license plate recognition is based on a set of frames. To disable tracking and license plate recognition for each frame separately without reference to the previous frames, and the quality can vary from 0% to 100%, select the No value |
No | ||
VodiCTL_VPW_DYNAMIC_OUTPUT_ PERIOD | 0.5 | Specify the time period in seconds for which the recognition result must be output. You can use this parameter only if the VodiCTL_VPW_DYNAMIC_WITH_DUPLICATE parameter is enabled. The value must be in the range [0, 3600] |
VodiCTL_VPW_DYNAMIC_OUTPUT_ TIMEOUT | 1 | Specify the minimum required time of license plate monitoring in seconds before the recognition result is output to the user. You can use this parameter only if the VodiCTL_VPW_DYNAMIC_ENABLE parameter is enabled. In this mode, the vehicle track is monitored, and the user doesn’t receive the license plate recognition result immediately, rather after the time specified in this parameter. In this case, the first recognition result will be replaced by a better one and subsequently output to the user. If you specify the 0 value for this parameter, you will receive the first recognition result. Note that after the time specified in this parameter has elapsed, the monitoring of the license plate track continues until it disappears from the frame. The value must be in the range [0, 3600] |
VodiCTL_VPW_DYNAMIC_WITH_ DUPLICATE | Yes | By default, periodic output of license plate recognition results is enabled. To disable the periodic output of results, select the No value |
No | ||
VodiCTL_VPW_IMAGE_BLUR | 13 | Parameter used for internal requirements. We recommend specifying the 13 value. The value must be in the range [0, 100000] |
VodiCTL_VPW_LOG_SETTINGS | Yes | By default, the parameter is disabled. To enable logging of all recognition parameters to the log file, select the Yes value |
No | ||
VodiCTL_VPW_PLATE_FILTER_ RODROPFACTOR | 0 | Specify the coefficient of license plates filtering by image density (second strategy). Type is unsigned. This coefficient is used during image binarization and has optimal values, which are determined by developers using their own test samples. The parameter is considered a service parameter, and its value must be set according to the recommendations of technical support specialists. The value must be in the range [0, 100000] |
VodiCTL_VPW_PLATE_FILTER_ ROFACTOR | 95 | Specify the coefficient of license plates filtering by the so-called image density—the ratio of white pixels to the total number of pixels (first strategy). Type is unsigned. This coefficient is used during image binarization and has optimal values, which are determined by developers using their own test samples. The parameter is considered a service parameter, and its value must be set according to the recommendations of technical support specialists. The value must be in the range [0, 100000] |
VodiCTL_VPW_PLATE_FILTER_ SYMCOUNT | 0 | Enable/disable the algorithm of simple license plate filtering by the minimum number of recognized characters on the plates. If the algorithm is enabled (the parameter value is greater than 0), a basic search for characters on the license plate candidate (geometry, proportions) is performed. If fewer characters are detected on the candidate than the value of this parameter, this candidate isn’t considered a license plate. That is, the value of this parameter is the minimum number of characters that must be present on a license plate candidate when the basic algorithm is running. The value must be in the range [0, 100000] |
VodiCTL_VPW_PLATE_STAR_MAX | 0 | Specify the maximum number of unrecognized characters on the license plate, at which the result is still considered the result of license plate recognition. The value must be in the range [0, 100000] |
VodiCTL_VPW_TEXT_WITH_PUNCTUATION (Advanced) (starting with Detector Pack 3.12) | Yes | Only for Germany and Taiwan. The parameter divides the characters on the license plate by hyphens into groups that determine the city/area and a group of the unique part of the license plate. By default, recognized license plate characters are displayed without hyphen. If you want to display recognized license plate characters with a hyphen, select the Yes value |
No | ||
Advanced settings Attention! Advanced configuration of the detector must be performed with the assistance of AxxonSoft technical specialists. | ||
Advanced image analysis | Yes | By default, the parameter is disabled. Under normal conditions, this parameter doesn’t affect the detection quality. Under poor conditions (for example, if the camera characteristics/settings don’t fully meet the requirements, or detection occurs in bad weather), to improve the recognition quality, select the Yes value. This will increase the frame processing time by 20-30% depending on the frame size |
No | ||
Algorithm of recognition of distorted LP image | Yes | By default, the algorithm of recognition of distorted license plate image is disabled. If you want to recognize license plates that are at a sharp angle to the camera, select the Yes value |
No | ||
Contrast threshold | 40 | Specify the image contrast threshold. We recommend increasing the value up to 50-60 on a good quality image, on an image with poor contrast, the value must be reduced. The value must be in the range [0, 100] |
Frame size change | 1920 | The analyzed frames are scaled down to a specified resolution (1920 pixels on the longer side) by default. The following algorithm is used:
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) | 0 | By default, the license plate recognition event is generated after the license plate track disappears from the frame. It is possible to generate a recognition event either after expiration of the time specified in seconds in the Event timeout parameter, or after reaching the similarity percentage specified in the LP display quality parameter. If the value of both parameters is different from 0, the recognition event will be generated when the first of the two conditions is met. The value must be in the range [0, 3600] |
GDPR policy | - | By default, on the layout and in the archive, the characters of a license plate are completely hidden "GDPR ON". To display the characters of a license plate, you must enter a value: "-"—hide all characters (default value), " (blank field of a parameter value)"—show all characters, "N-"—hide the first N characters, "-N"—hide the last N characters, where N is the number of characters |
LP advanced search algorithm | Yes | By default, the parameter is disabled. If license plates of different sizes will be present in the frame, select the Yes value. |
No | ||
LP display quality | 0 | Attention! The value of the LP display quality parameter must not be less than the value of the Minimum similarity parameter. By default, the license plate recognition event is generated after the license plate track disappears from the frame. It is possible to generate a recognition event either after expiration of the time specified in seconds in the Event timeout field, or after reaching the similarity percentage specified in the LP display quality field. If the value of both parameters is different from 0, the recognition event will be generated when the first of the two conditions is met. The value must be in the range [0, 100] |
Maximum number of threads | 1 | Specify the maximum number of recognition threads. If the value is 0, the recognition process takes place in the same thread that starts it. The value must be in the range [0, 10]. Attention!
|
Minimum similarity | 40 | Specify the minimum percentage of similarity between the recognition result and the corresponding license plate template, at which this result can be considered a license plate recognition result. This parameter is used to filter the obtained results by validity. 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
|
Basic settings | ||
Algorithm for detecting vehicle direction | By 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 | ||
Analysis mode | Standard (Morph) | Select the analysis mode of the detector: standard or neural network mode |
Advanced (DNN) | ||
Detection mode | CPU | Select the processor for the operation of the detector algorithm (see Hardware requirements for the License plate recognition VT, Selecting Nvidia GPU when configuring detectors).
|
Nvidia GPU 0 | ||
Nvidia GPU 1 | ||
Nvidia GPU 2 | ||
Nvidia GPU 3 | ||
License type | Search in archive | Standard license for searching recognized license plates in the archive. Attention! This type of license provides a 30-second delay between the license plate recognition and the corresponding event (see Vehicle license plate recognition and search). |
Normal (25 FPS or 6 FPS) | The 25 FPS license has a priority. If you don't have the 25 FPS license, the 6 FPS license is used. You cannot use the license plate recognition function if you haven't purchased both licenses | |
Fast (25 FPS) | The Fast license allows you to process video streams at up to 25 FPS. License plate recognition for vehicles moving at speeds up to 150 km/h. You cannot use the license plate recognition function if you haven't purchased the license | |
Slow (6 FPS) | The Slow license allows you to process video streams at up to 6 FPS. License plate recognition for vehicles moving at speeds up to 20 km/h. You cannot use the license plate recognition function if you haven't purchased the license | |
Attention! All license types except the standard one (Search in archive) require the hardware key or the software key activation (see Licensing of the software module for the License plate recognition VT in Windows OS). | ||
Maximum LP width | 20 | 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!
|
Minimum LP width | 5 | |
Minimum number of detection triggers | 6 | Specify the minimum number of events to display the object track. The higher the value of this parameter, the longer the time from object detection to displaying its track. A low value of this parameter can result in false events. The value must be in the range [1, 20] |
Country selection | ||
Country 1 name | Albania, Algeria, Andorra, Argentina, Armenia, Australia, Austria, Azerbaijan, Bahrain, Brunei, Belarus, Belgium, Bolivia, Bosnia and Herzegovina, Botswana, Brazil, Bulgaria, Canada, Chile, Colombia, Croatia, Czech Republic, Denmark, Ecuador, El Salvador, Estonia, Finland, France, Georgia, Germany, Greece, Guatemala, Honduras, Hong Kong, Hungary, India, Indonesia, Iran, Israel, Italy, Jordan, Korea, Kazakhstan, Kenya, Kyrgyzstan, Latvia, Liechtenstein, Sri Lanka, Lithuania, Luxembourg, Malaysia, Malta, Mexico, Moldova, Monaco, Mongolia, Montenegro, Nicaragua, Nigeria, Norway, Panama, Paraguay, Peru, Philippines, Poland, Portugal, Romania, Russian Federation, Serbia, Singapore, Slovakia, Slovenia, South Africa, Spain, Sweden, Switzerland, Taiwan, Tajikistan, Tunisia, Turkey, Turkmenistan, USSR, Ukraine, United Kingdom of Great Britain and Northern Ireland, Uruguay, USA, Uzbekistan, Vietnam, Zambia, Not used | In the corresponding fields, select from the list one or more countries whose license plates you want to recognize. Attention!
|
Country 2 name | ||
Country 3 name | ||
Country 4 name | ||
Country 5 name |
By default, the entire frame is the detection area. If necessary, in the preview window, you can reduce the rectangular detection area (see Configuring a detection area).
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 VT is complete. If necessary, you can create and configure the necessary sub-detectors on the basis of the License plate recognition VT (see Standard sub-detectors).