Page History

VodiCTL_VPW_PLATE_RATIO_TYPE

Information about how much the initial image is reduced or increased in height. The default value is 0. There are three options available:

1. No distortions

2. Automatically depending on the image size

2. User value

VodiCTL_VPW_IMAGE_THRESHOLD

Base level of image thresholding.

The default value is 40

VodiCTL_VPW_IMAGE_BLUR

The parameter for internal use. The recommended value

is 13

VodiCTL_VPW_ PLATE_EXTRA_ANGLE_ANALYSE

Enable/disable the angle analysis algorithm of the license plate image

VodiCTL_VPW_PLATE_STAR_MAX

Maximum unrecognized

characters on the license plate

at which the result will still be considered the result of the recognition of the license plate

VodiCTL_VPW_PLATE_PROBABILITY_MIN

Minimum percentage of similarity between the recognition result and the corresponding license plate

template at which this result can be considered the result of the recognition of the license plate. Using this parameter, the results obtained are filtered according to the authenticity

VodiCTL_VPW_PLATE_FILTER_ROFACTOR

VodiCTL_VPW_PLATE_FILTER_RODROPFACTOR

The license plate filter coefficient by the so-called image

density—ratio of white pixels to total pixels (second strategy). The type is unsigned. This coefficient is used for image thresholding and has the optimal values, which are determined by AutoSDK developers using their own test samples. The parameter is considered as a service one, and its value

must be set according to the recommendations of technical support specialists

VodiCTL_VPW_PLATE_FILTER_SYMCOUNT

Enable/disable the algorithm of simple license plates filter

by the minimum number of recognized

characters on them. If the algorithm is enabled (the value of the parameter is greater than 0), the base search for

characters on the

license plate candidate (geometry, proportions) is performed. If

fewer characters are recognized on the

license plate candidate than specified in this parameter, this

license plate candidate is not considered a license plate. That is, the value of this parameter is the minimum characters that must be present on the

license plate candidate when the basic algorithm is

used

VodiCTL_VPW_LOG_SETTINGS

Enable/disable logging of all recognition parameters

VodiCTL_VPW_PLATE_PRECISE_ANALYSE

Enable/disable precise image analysis. It increases the quality of recognition under adverse conditions (for example, if the characteristics/settings of the camera do not fully meet the requirements or in bad weather). It increases the processing time of the frame by 20-30%, depending on its size. Under normal conditions, this parameter does not affect the quality of recognition

Enable/disable

dynamics of license plate recognition (by default,

the dynamics is enabled).

If the value is True, then tracking is enabled, and the

license plate is recognized by the set of frames.

If the value is False, then tracking is disabled,

and the license plate is recognized by each frame separately without taking to account the previous ones, and the quality can vary from

0% to 100%

VodiCTL_VPW_DYNAMIC_OUTPUT_FRAMECOUNT

Number of frames required to display a license plate. The default value is 0. This is necessary, but not sufficient, for the first output of the result. This condition delays displaying from the first moment of recognition of the license plate in dynamics. The setting is designed to improve authenticity of the results, as well as to hide possible false

events

VodiCTL_VPW_DYNAMIC_WITH_DUPLICATE

Enable/disable the periodic output of license plate recognition results

VodiCTL_VPW_DYNAMIC_OUTPUT_TIMEOUT

The minimum time required to monitor the license plate (in milliseconds) before displaying the recognition result to the user. This parameter can only be used when the “Dynamic” mode is on. In this mode, the

track of the vehicle is monitored, and the user does not immediately receive the recognition result of the license plate, but after the time specified for this setting. In this case, the first recognition result will be replaced by the result of higher quality and subsequently displayed to the user. If parameter 0 is set for this value, the user gets the first result of recognizing the detected license plate.

After the time specified in this parameter expires, the monitoring of the

track of the license plate continues until it disappears from the frame

VodiCTL_VPW_DYNAMIC_OUTPUT_PERIOD

Time period (in milliseconds) over which the recognition result

must be displayed to the user. This parameter can be used only if the VodiCTL_VPW_DYNAMIC_WITH_DUPLICATE parameter is set

VodiCTL_VPW_DYNAMIC_DURATION_WITHOUT_ACCESS

Maximum permissible absence time of the license plate in the monitoring

area (in milliseconds). After this time, the license plate is considered

lost and is displayed to the user with the set checkbox

VodiF_RESULT_LOST

Time interval (in milliseconds) that affects the algorithm for comparing the preliminary recognition results.

That is, if the results fall within a given interval and the geometric distance between the

license plates is small compared to the

license plates size, then it is considered to be the same object

VodiCTL_VPW_DNN_DEVICES

A list of devices on which the deep neural network (DNN) computations

is performed. The set of available devices is defined in the <Vodi/devType.h> file.

This parameter can also be set via the Windows environment variable: VPW_DNN_DEVICES={comma-separated list of devices}. For example: CPU, GPU, MYRIA

VodiCTL_VPW_PLATECANDS_METHODS

A variety of methods for obtaining the

license plate candidates. Available methods:

• VodiF_VPW_PLATECANDS_BY_MORPH

• is an old method;
• VodiF_VPW_PLATECANDS_BY_DNN is a method based on deep neural networks (DNN);
• VodiF_VPW_PLATECANDS_BY_2_DNN

• is a new method based on deep neural networks (DNN), it is set by default. We recommend using this method.

To ensure the operation in the VodiF_VPW_PLATECANDS_BY_2_DNN and VodiF_VPW_PLATECANDS_BY_DNN

modes, it is important to correctly set the minimum size of the

license plate on the image; the larger it is (for example, from 100 pixels or more), the higher the performance will be.

This parameter can also be

set via the Windows environment variable: VPW_PLATECANDS_METHODS={number}. For example: 1, 2

VodiCTL_VPW_ANALYSE_LEVEL

The level of the

license plate analysis. The following levels of analysis are available:

• VodiK_VPW_

• PLATECANDS_ANALYSE—only license plate candidates are found at this level, that is, the rectangles of their areas;
• VodiK_VPW_

• SYMCANDS_ANALYSE—the character candidates are also be found at this level, that is, the rectangles of their areas;
• VodiK_VPW_TEXT_ANALYSE—the complete license plate analysis is performed at this level;
• VodiK_VPW_

• TEMPLATE_ANALYSE—the found characters are also recognized at this level

• . Performs full license plate analysis, set by default

VodiCTL_VPW_PLATE_ANALYSE_METHODS

A variety of methods for analyzing the

license plate candidates. Available methods:

• VodiK_VPW_PLATE_ANALYSE_METHODS_DEFAULT

• ,
• VodiF_VPW_BLURAN,
• VodiF_VPW_NAN,
• VodiF_VPW_TMPLAN,
• VodiF_VPW_DNNAN, 
• VodiF_VPW_OTSUAN

• ;
• VodiF_VPW_

• DNN2AN is a new

• license plate analysis method based on deep neural networks (DNN).

• Set by default. We recommend using this method.

The VodiF_VPW_DNN2AN | VodiF_VPW_BLURAN | VodiF_VPW_DNNAN | VodiF_VPW_TMPLAN methods provide the highest number of correctly recognized results

VodiCTL_VPW_PLATE_DNN_FILTER_ENABLE

Enable/disable the

filtering

of license plate candidates by the deep neural network (DNN)

VodiCTL_VPW_TREAT_PLATECAND_AS_PLATE

Enable/disable the ability to consider each license plate candidate as a

license plate. This means that if the analysis of a candidate was unsuccessful for any reason (for example, it was not possible to recognize the

license plate), then such a candidate will not be lost, but will be given as a

license plate, while some of the information will be missing, namely the pis_plate_variantc will be 0

VPW_RECOGN_OUTSIDE_PLATECAND

This Windows environment variable makes it possible to prohibit the analysis of a

license plate outside the rectangular area (that is, a license plate candidate

) found by the license plate detector. This is an experimental parameter and it

can be removed later

VodiCTL_VPW_SEQUENTIAL_FLUSH_ENABLE

Enable/disable the ability to change the behavior of the VodiprincFlush operation. Without this parameter, the operation

waits for the completion of the analysis of all frames, then

transfers the results to the dynamics (if enabled),

accumulates the dynamics results,

performs the flush operation for the dynamics and finally

returns the accumulated result.

With this parameter, the operation waits for the completion of the analysis of the earliest frame, then transfers its result to the dynamics (if enabled) and returns its result. Thus, to get all the results that are still being analyzed, it is necessary to sequentially call the VodiprincFlush operation while it returns the >=BoS_OK status

VodiCTL_VPW_TREAT_SYMBOLS_AS_TEXT

Allows you to interpret recognized characters as text if, for example, there are problems with template recognition or if the recognized license plates don't match known templates