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

Previous page Licensing of the software module for the Vehicle recognition XR in Windows OS  Installing and configuring Vaxtor License Server using Docker for Vehicle recognition XR Next page

Hardware requirements for the Vehicle recognition XR

Video stream and scene requirements for the Vehicle recognition XR

Image requirements for the Vehicle recognition XR

Licensing of the software module for the Vehicle recognition XR in Windows OS

To configure the Vehicle recognition XR detector, do the following:

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

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 Check in lists 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
Video stream

Main 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
NameVehicle recognition XREnter 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
TypeVehicle recognition XRName of the detector type (non-editable field)
Basic settings
Algorithm for detecting vehicle directionBy LP coordinatesThe 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 vehicle 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 vehicle scale change
Event timeout0Specify the time in seconds after which an event must be generated after recognizing a license plate in the frame. If the value is 0, an event is generated after the track with a license plate is lost. The value must be in the range [1, 60]
Frame size change1920

The analyzed frames are scaled down to a specified resolution (1920 pixels on the longer side) by default. The value must be in the range [640, 10000]. The following algorithm is used:

  • 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, 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.

LP recognition advanced settings
Country pattern compliance
YesThe parameter is enabled by default. To disable the check of country pattern compliance, select the No value
No
Extra processing for LP searchYesThe parameter is disabled by default. To enable the extra processing for LP search, select the Yes value
No
Frame processing period (sec)1Specify the period of frame processing in seconds. The value must be in the range [0, 999]
Maximum height of licence plate characters (pixels)70

Specify the maximum height of licence plate characters in pixels. The value must be equal to or greater than the value in the Minimum height of licence plate characters (pixels) parameter. The value must be in the range [34, 70]

Note

  • For license plates with different character size, such as those of Middle Eastern countries, the maximum height is applied to the largest set of characters found in the license plate.
  • The optimal character size for recognition is 22–24 pixels.
  • Characters less than 18 pixels high increase the likelihood of misrecognition as details of the character shape can be lost, especially if the image quality is poor: a 'G' can turn into a 'C', and so on.
  • Characters more than 55 pixels high can take much longer to process.
Maximum Levenshtein distance1

Specify the maximum Levenshtein distance between license plate characters. The value must be in the range [0, 999].

This parameter is used to determine what makes a license plate different from the previous license plate (Levenshtein distance). For two identical readings, the Levenshtein distance is zero. This parameter helps to reduce false positives when a license plate is read several times before a result is given and a partial reading still represents a valid license plate.

Example: real license plate is "AB-4567".

  • reading 1: AB-4567
  • reading 2: AB-456

If the maximum distance is set to 0 (exact match), the system reports two license plates. But if the distance is set to 1 (or greater), the system reports the first license plate, but not the second one. This is because a license plate with one distinct character is considered a readout of the same license plate, that is, a probable misreading has occurred

Note

  • For the countries where the minimum number of characters in license plates is greater than 5, we recommend setting the value to 2 or greater.
  • For the countries where license plates can have 5 or fewer characters, set this value to 1.
Maximum LP slope angle40Specify the maximum slope angle of the license plate. The value must be in the range [0, 999]
Maximum number of same LP readings10Specify the maximum number of readings of the same license plate. The value must be in the range [1, 999]
Minimal number of characters in LP2Specify the minimum number of characters in a license plate. The value must be in the range [2, 16]
Minimum authenticity threshold80Specify the minimum value of recognition authenticity as a percentage. The value must be in the range [1, 100]
Minimum characters confidence threshold80Specify the minimum threshold value of license plate recognition confidence as a percentage. The value must be in the range [1, 100]
Minimum height of licence plate characters (pixels)14Specify the minimum height of license plate characters in pixels. This is the distance between the top pixel of the character and the bottom pixel. The value must be in the range [14, 70]
Minimum number of same LP readings1

Specify the minimum number of readings of the same license plate.

For example, if you set the value to 2, you will receive a massage about a license plate only if two identical readings have been made. The value must be in the range [1, 999]

Recognition algorithm complexity


Low level

Select the complexity level of recognition algorithm from the list. The Medium level is selected by default

Note

  • The higher the complexity of the algorithm, the longer the processing time.
  • Depending on the images, the difference between the low and high complexity level can be up to 4%, but on average the difference is about 2 or 3%.
  • If image is of high quality and license plates have a standard shape, the difference between medium and high level doesn't matter. You can set the Medium level to make license plate processing faster.
  • We recommend using the Low level only in complex scenes, low computing power, and when vehicle detection is preferred over license plate recognition.
Medium level
High level
Recognition timeout (sec)0Specify the recognition timeout in seconds. The value must be in the range [0, 999]
LP recognition basic settings
Country 1 name

Albania, Algeria, American Samoa, Andorra, Angola, Anguilla, Antigua and Barbuda, Argentina, Armenia, Aruba, Australia, Austria, Azerbaijan, Bahamas, Bahrain, Barbados, Belarus, Belgium, Benin, Bermuda, Bhutan, Bolivia, Bosnia, Botswana, Brazil, Brunei, Bulgaria, Burkina Faso, Burundi, Cambodia, Cameroon, Canada, Cape Verde, Cayman Islands, Central African Republic, Chad, Chile, Christmas Island, Colombia, Comoros, Congo, Cook Islands, Croatia, Cyprus, Czech Republic, Denmark, Dominica, Dominican Republic, East Timor, Ecuador, Egypt, El Salvador, Equatorial Guinea, Estonia, Faroe Islands, Fiji, Finland, France, French Guiana, French Polynesia, French Southern Territories, Gabon, Gambia, Georgia, Germany, Ghana, Gibraltar, Great Britain, Greece, Greenland, Grenada, Guadeloupe, Guatemala, Guinea, Guyana, Haiti, Honduras, Hong Kong, Hungary, Iceland, India, Indonesia, Ireland, Israel, Italy, Ivory Coast, Jamaica, Jordan, Kazakhstan, Kenya, Kiribati, Kosovo, Kuwait, Kyrgyzstan, Laos, Latvia, Liberia, Liechtenstein, Lithuania, Luxembourg, Macau, Macedonia, Madagascar, Malawi, Malaysia, Mali, Malta, Marshall Islands, Martinique, Mauritania, Mauritius, Mayotte, Mexico, Micronesia, Moldova, Monaco, Mongolia, Montenegro, Morocco, Mozambique, Namibia, Nauru, Netherlands, Netherlands Antilles, New Caledonia, New Zealand, Nicaragua, Niger, Nigeria, Northern Mariana Islands, Norway, Oman, Pakistan, Panama, Papua New Guinea, Paraguay, Peru, Philippines, Poland, Portugal, Qatar, Reunion Island, Romania, Russia, Rwanda, Saint Kitts and Nevis, Saint Lucia, Samoa, San Marino, Sao Tome and Principe, Saudi Arabia, Senegal, Serbia, Seychelles, Singapore, Slovakia, Slovenia, Solomon Islands, South Africa, South Sudan, Spain, Sri Lanka, Swaziland, Sweden, Switzerland, Taiwan, Tajikistan, Tanzania, Thailand, Togo, Tonga, Trinidad and Tobago, Turkey, Turkmenistan, Turks and Caicos Islands, Uganda, Ukraine, United Arab Emirates, United Kingdom, United States, Uruguay, Uzbekistan, Vatican, Venezuela, Vietnam, Virgin Islands British, Virgin Islands USA, Wallis and Futuna Islands, Zambia, Zimbabwe, Not used

In the corresponding fields, select from the list one or more countries, the license plates of which you want to recognize


Country 2 name
Country 3 name
Country 4 name
Country 5 name
Vehicle recognition advanced settings
Minimum vehicle recognition confidence threshold50Specify the threshold value of the minimum vehicle recognition confidence as a percentage. The value must be in the range [1, 100]
Vehicle analytics qualityLow levelSelect the quality of the vehicle analysis from the list. The Medium level is selected by default
Medium level
High level
Vehicle recognition basic settings
Vehicle recognitionYesThe parameter is disabled by default. To enable the vehicle recognition, select the Yes value
No

By default, the entire frame is analyzed. If you want to analyze only a part of a frame, in the Surveillance window, specify the area in which detection and recognition of vehicles 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.
  • To hide the detection area, click the button. To cancel the action, click this button again.
  • To delete the selected area, click the button.

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

Configuration of the Vehicle recognition XR is complete.

  • No labels