Page History

x32: (x32)\FRS
x64: (x64)\FRS

The key defines on how many CPU cores the face recognition module will operate (firserver.run process). All cores are in use by default.

The key sets the timeout upon which Face Server ‘loses’ the face if there is no new data about it.

Sets the parameters of generating and attaching face biometrics in the detection tool:

1 – Face detection tools generate and attach face biometrics to the photo. 

0 – Face detection tools do not generate face biometrics - the face is only captured.

Note. Face recognition Server that performs search in the user database checks up whether it has attached biometrics when it gets a face photo. If yes, then biometrics are not further generated for search in the database - data attached to the photo is in use. If no, then recognition Server generates biometrics itself using the photo. 

Specifies what data will be stored in the database when using the Face recognition Server:

1 - all captured faces.
0 - only the faces about which there are recognition results.

The key is in use in order to avoid the database overflow.

Note. Since version 6.2 use the UseFaceDB key in order to minimize the amount of data stored in DB.

The key is used to configure the face detection tool – it sets time on the expiry of which the face is considered lost.

For instance, if timeUntilLost = 1 and a man covers his face with the hands in front of the camera and then shows it again, then the face detection tool does not capture it as it considers that the face was lost for the time it was covered.

The key sets the mode for storing metadata, images and vectors of captured and reference faces.

0 – metadata, images and vectors are stored only in database.

1 – metadata, images and vectors are stored in database, images and vectors are also storing in a folder on disk. Path to folder is specified using the FaceDB parameter(it is possible to specify both a local and network folder).

2 – metadata are stored in the database, images and vectors are storing only in a folder on disk. Path to folder is specified using the FaceDB parameter (it is possible to specify both a local and network folder).

CpuCoreCountAddPerson

The key defines the number of CPU cores where the vectors of persons are generated when adding a reference face to the database.

0 - vectors are generated on the number of cores specified in the CpuCoreCount key. The cores are used successively. Recognition sample is bound to each core. 

1 - only 1 fixed core (different from those specified in CpuCoreCount) is in use when adding a reference face to the database. 

2 - only 2 fixed cores (different from those specified in CpuCoreCount) are in use when adding a reference face to the database.

Face.HardwareCPU

The key defines the order of binding streams to CPU cores when generating vectors of persons.

no value or 0 - streams are bound randomly to CPU cores.
1 - streams are bound successively to CPU cores depending on their total number. 
2 - streams are bound to first cores of each CPU.

Mechanism of displaying faces. When a new mechanism of displaying is enabled, the photo in the list of captured faces is not duplicated - it is updated in the same cell while the tracker "sees" it.  

0 - new mechanism of displaying faces. 

1 - old mechanism of displaying faces. 

The key enables saving the last recognized face and all its necessary data to a file. This image file can be sent directly to the recognition server via the iidk_client utility.

0 - General operation mode.

1 - When the face is captured, the captureFrame (cam_N) .log file is created (where N is the camera number that captured the face) in the <Intellect Installer directory>\Modules (64)\ folder. This file will contain the last recognized face and all its necessary data. This image file can be sent directly to the recognition server via the iidk_client utility.

Note. The file is overwritten every time a new face is captured.

The key restricts resolution (width) of the photo when adding it to the faces database.

Set greater value to the key if the following message appears when adding a face to DB: "Adding error. The face was not added. Insufficient image quality to add".

The key restricts resolution (height) of the photo when adding it to the faces database.

The key enables selecting the Tevian algorithm.

0 – less resource intensive algorithm is in use

1 – more resource intensive algorithm is in use 

Important! Biometric vectors received using this algorithm cannot be used with alternative one. For proper operation of Face Intellect after changing this parameter biometric vectors are to be converted as described in Transition between face recognition modules section. 

An alternative algorithm for filtering false triggerings of the tracker. This key is in use if Tevian.GlobalTrackingDetectionFilter=0 and Tevian.DetectionFilterValue > 0 (see the corresponding parameters below). 

0 - ALG1

1 - ALG2

Note. It is not recommended to change this parameter without consulting Tevian.

Configuring alternative algorithm filtering. It is in use if the value ofTevianof Tevian.GlobalTrackingDetectionFilter if is more than 0 (see the corresponding parameter below).

Note. It is not recommended to change this parameter without consulting Tevian.

Activates an additional check to filter out false triggerings of the tracker. If faces in masks are not recognized, it is recommended to disable this check, however, this can cause false triggerings of the tracker.

0 - disabled

1 - enabled.

Note. It is not recommended to change this parameter without first consulting with Tevian.

Face detection operation mode (identification). The recommended parameter value is 0.

0 - ALG1

1 - ALG2

Note. It is not recommended to change this parameter without consulting Tevian.

This parameter affects the detector captioning capacity. If there is a great value, the tracks can rend.

Note. It is not recommended to change this parameter without consulting Tevian.

Face detector confidence threshold (do not confuse with face quality).

Note. It is not recommended to change this parameter without consulting Tevian.

The key enables selecting the Tevian algorithm for recognition and face search.

0 - ALG1 less resource-intensive algorithm is in use.

1 - ALG2 identification of the higher quality, but more resource-intensive.

2 - PRECISE the highest quality of recognition, but the most resource-intensive. This algorithm is recommended if significantly less time is spent on face recognition than on detection (if there are few people in the frame).

Important! Biometric vectors received using this algorithm cannot be used with any other one. For proper operation of Face Intellect after changing this parameter biometric vectors are to be converted as described in Transition between face recognition modules.

The number of seconds to accumulate the best frames for recognition in the track. The longer the time, the poorer is the accuracy of the age determinination.

Note. For example, if the 1 second value is set, the average error in determining the age will be 2-3 years, and if the 5 seconds value is set, it will be 3-4 years.

Time since the last recognition after which the track is considered ended.

Note. It is not recommended to change this parameter without consulting Tevian.

Face.PollTime

The key specifies the polling time of the HUAWEI server in milliseconds.

Note. Face-Intellect requests the events only since the time it is launched. If events contain an earlier time than the launch time of Face-Intellect, these events will be ignored. That is why the HUAWEI server time and the Face-Intellect time should be synchronized.

AUTO Intellect

Registry section

Available values

Default

Product version

Parameter in effect

x32: (x32)\LPRVIEWER
x64: (x64)\LPRVIEWER

protocollimit

<1000

-

4.7.5 and later

Sets number of lines shown in the protocol (this parameter is for testing only).

x32: (x32)\radar
x64: (x64)\radar

EmulateRefreshSpeed

1 - 2147483647

100

4.7.5 and later

Radar emulator. Sets time period (ms) for refreshing data about speed in the radar emulation mode. 0 value blocks data refreshing.

x32: (x32)\radar
x64: (x64)\radar

WriteSpeedOnTitles

0, 1

0

4.7.5 and later

Defines whether to write speed values on titles.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

DisableUrmOutput

0, 1

0

4.7.5 and later

Disables results output.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

GlobalUrmDebug

0, 1

0

4.7.5 and later

Enables displaying CZoneInfo objects in dbgview. 

x32: (x32)\URMLPR
x64: (x64)\URMLPR

OneSpeedDetect

0, 1

0

4.7.5 and later

Enables filtering the radar speed values.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

ReadSpeedFromTitles

0, 1

0

4.7.5 and later

Defines whether to read speed from titles or not.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

TestWidth

-

0

4.7.5 and later

 Image width change (internal use only).

x32: (x32)\URMLPR
x64: (x64)\URMLPR

TestHeight

-

0

4.7.5 and later

 Image height change (internal use only).

x32: (x32)\URMLPR
x64: (x64)\URMLPR

Time

-

-

4.7.5 and later

Saves time of the last viewed archive fragment in the test mode.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

UrmDebug

0, 1

0

4.7.5 and later

Enables recording of  tiff files to UrmDebug folder.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

UrmSendProcessEvents

0, 1

0

4.7.5 and later

Sends beginning (VEHICLES_BEGIN) and ending (VEHICLES_END) parameters of license plate recognition to the core.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

UseTry

0, 1

0

4.7.5 and later

Enables the seh module.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

WriteUraganErrorBuf

0, 1

0

4.7.5 and later

If failure occurs, the uragan.buf file is created (only of UseTry=1). 

x32: (x32)\URMLPR\UnitTest
x64: (x64)\URMLPR\UnitTest

CountryName

Text

RUS

4.7.5 and later

Sets the test country name.

x32: (x32)\URMLPR\UnitTest
x64: (x64)\URMLPR\UnitTest

Enabled

0, 1

0

4.7.5 and later

Enables/disables test.

x32: (x32)\URMLPR\UnitTest
x64: (x64)\URMLPR\UnitTest

ExecuteSecond

> = 0

3

4.7.5 and later

Sets time of test execution.

x32: (x32)\URMLPR\UnitTest
x64: (x64)\URMLPR\UnitTest

Number

Text

M038EH150

4.7.5 and later

Sets the test number.

x32: (x32)\URMLPR\UnitTest
x64: (x64)\URMLPR\UnitTest

PlateHeightPercent

> 0

15

4.7.5 and later

Sets the test license plate height.

x32: (x32)\URMLPR\UnitTest
x64: (x64)\URMLPR\UnitTest

PlateWidthPercent

> 0

25

Sets the test license plate width.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

ParkingMode

0, 1

-

5.0

Enabling the parking mode for the CARMEN-Auto recognizer:

1 – parking mode is enabled. Recognition starts at ULPR|START reaction. As soon as one license plate is recognized, the recognition stops.

0 – parking mode is disabled. Recognition continues till getting the ULPR|STOP reaction. 

Important! For correct operation of the key make sure that the Enable on motion detection trigger checkbox is set on the settings panel of the LPR channel object corresponding to the CARMEN-parking recognition module (see Setting the joint operation of the LPR channel and the motion detector of the Intellect platform).

Note. The ULPR|START and ULPR|STOP reactions are created using the scripts. Operator command, sensor triggering, motion detection tool triggering, etc. can cause the reaction.

Enabling the parking mode for the CARMEN-Auto recognizer:

1 – parking mode is enabled. Recognition starts at ULPR|START reaction. As soon as one license plate is recognized, the recognition stops.

0 – parking mode is disabled. Recognition continues till getting the ULPR|STOP reaction. 

Note. If you set the 1 value on the settings panel of the LPR channel object, the Enable on motion detection trigge checkbox will be automatically set without the possibility of removing it until this key value is set to 0 (see Setting the joint operation of the LPR channel and the motion detector of the Intellect platform).

Note. The ULPR|START and ULPR|STOP reactions are created using the scripts. Operator command, sensor triggering, motion detection tool triggering, etc. can cause the reaction.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

When value = 1, the key allows saving frames transmitted from Intellect to the CARMEN Parking / CARMEN-Auto module.

• For CARMEN Parking the frames are saved to the following folders:
  < Intellect installation folder>\Modules\CPD_RawResults\idDetector\ - frames with data for recognition.
  <Intellect installation folder >\Modules\CPD_RawResults\idDetector\NotFound – frames with no data for recognition.If value = 0, then frames are not saved.

• For CARMEN Auto the results are stored to the <Intellect>\Modules\CarmenResults\idDetector\ folder. The results are represented by pairs of files: ‘<recognition time in UTC format>.bmp’ file (with a frame to be recognized) and xml file with settings of the recognizer and recognition results.

• If the module is restarted, the Apply button is clicked or 5000 files are saved, then the specified folder and the data in it are automatically deleted and the folder is recreated. 

When value = 1, frames are not saved.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

x32: (x32)\URMLPR
x64: (x64)\URMLPR

x32: (x32)\URMLPR
x64: (x64)\URMLPR

Sets time (in milliseconds) corresponding to the delay with which events about green/red traffic lights are received.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

x32: (x32)\URMLPR
x64: (x64)\URMLPR

The key enables the multi-stream mode emulation in IntLab.

0 – license plates recognition is performed when the ray, specified on the settings panel of the IntLab-Carriages module object, is open or closed (see Setting up the IntLab-Carriages module).

x32: (x32)\URMLPR
x64: (x64)\URMLPR

The key includes the multichannel mode emulation for the IntLab-Carriages module.

0 –  LP number recognition is carried out using macro specified on the IntLab-Carriages module object settings panel (see Setting up the IntLab -Carriages module).

1 –  when it is necessary to start the LP number recognition, the information on the time of occurrence is taken from subtitles added to a video.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

The key sets an algorithm of frame preparation before sending it to the Carmen license plate recognition module:

0 – frames are sent to the Carmen license plate recognition module without pre-processing.

1 – rectangular areas that may contain a license plate are searched in the frame. Only those rectangular areas that may contain a license plate are then forwarded to the Carmen license plate recognition module.

2 – if any rectangular area that may contain a plate number is detected on the frame, the frame in whole is forwarded to the Carmen license plate recognition module. If the Carmen license plate recognition module detects a license plate, it tries to find another plate number, and time for recognition increases as a result.

3 – if any rectangular area that may contain a plate number is detected on the frame, the frame in whole is forwarded to the Carmen license plate recognition module. If the Carmen license plate recognition module detects a license plate, it does not try to find another license plate.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

"FASTEST" – a speed trap sends speed of the fastest object to the Intellect software

"STRONGEST" – a speed trap sends speed of the biggest object to the Intellect software

Important! If values other than above are specified for the key, the Intellect software does not recieve speed data from speed traps.

x32: (x32)\URMLPR
x64: (x64)\URMLPR

x32: (x32)\URMLPR
x64: (x64)\URMLPR

The key specifies the time difference (in milliseconds) between the moments of receiving the frame and license plate recognition event, sufficient to allow these events to be linked. The key is to be in use if data about recognized license plates are not displayed on the On-line monitor in Auto Intellect, although there are recognition events in the Debug window.

RemoteLpr.x.NearestTime

X is the object identifier of the LP recognition channel in the Intellect software.

>=0

For the specified object of the LPR channel with the assigned remote recognition module, the key sets the time difference in milliseconds between the moments of receiving the frame and event on the LP recognition enough to bind these events. You should use the key if the data on the recognized LPs are not displayed in the Active Monitor of the Auto Intellect although they are found in the Debug window and Event protocol.

Specifies the way of storing images.

0 – metadata and images are stored only in the database.

1 – metadata is stored in the database, and images are stored in the local or network folder. Full path to the folder is specified by the LprDB.Path key (see above).

Note. Recognized LP numbers information is stored in the database regardless of the LprDB.Use key.

Specifies the amount of free storage space in a directory. When its limit is exceeded, the overwriting process starts, rewriting the oldest images with the most recent ones. The key is used if the LprDB.Use key value is 1 (see above).

The key enables the tracking of the recognized number disappearance and sets the time in milliseconds, after which the lost number event will be generated if this number has disappeared from the camera field of view.

0 - tracking of the recognized number disappearance is disabled.

>1 - after the specified time has passed, if the recognized number disappeared from the camera field of view, a lost number event will be generated.

The key enables saving the filtered numbers to the database.

0 - filtered numbers are saved to the database.

1 - filtered numbers are not saved to the database.

The key sets the display mode of the recognized Arabic numbers in the Event Log.

0 - Arabic number is displayed in two lines.

1 - Arabic number is displayed in one line.

The key sets the time in minutes, after which the violation detected by the main recognizer is ignored if the second recognizer, which is paired with the main one, also detected a violation.

The key activates the automatic restart by the timeout for the Auto-URAGAN recognition module if no recognition results are received from it.

The key disables the receiving of photos from the main cameras of the recognizers.

The key sets the number of frames that are stored in the buffer for the CARMEN-Auto module. It is applicable if there is skipping of numbers, but it may cause a delay in the numbers recognition.

The key sets the number of unprocessed frames that are stored in the buffer for all license plate recognition modules. It is applicable if there is skipping of numbers, but it may cause a delay in the numbers recognition.

The key activates the saving of the number recognition result in the * .jpg format for the Seenaptec module. As a result of the module operation, the AutoRecongitionResult folder will be created at the path: <Intellect installation directory>\Modules64\, into which the files with the following names will be saved: recognizer ID in Intellect - recognized number - violation <if any>.jpg.

Note. This setting is required for debugging.

The key sets the mode of determining the vehicle direction of movement of the vehicle.

0 - the direction is determined by the SDK.
1 - the direction is calculated by the position of the upper part of the number. If at the start of tracking the upper part of the number is lower than the upper part of the number at the end of tracking, then the direction is defined as “From camera”, otherwise “To camera”.
2 - the direction is calculated by the area of the LP number. If at the start of tracking the area of the number is larger than at the end of tracking, then the direction is defined as “From camera”, otherwise “To camera”.

The key sets the waiting time in seconds required for the number to appear if the vehicle is detected several times after stopping.

The key activates the mechanism for the IntLab-Carriages module that displays the frame where the number is the most visible, however, it causes a time delay in the displaying of the results.

The key activates the discarding of all tracks after the best frame which was defined by the recognition module.

The key activates an alarm if there is at least one number identification at the pedestrian crossing. Vehicle traffic is not taken into account.

Note. By default, the system tries to determine the traffic on a pedestrian crossing.

The key enables the entry of an Arabic LP number in the search field.

It is necessary to activate this key if the Persian calendar is used on the LPR channel.

Internal setting. Disables saving of frames from a synchronous video camera to the LprDB.Path folder and the [lprex].[dbo].[FramesSecondary] database.

0 - saving of all images from a synchronous video camera is disabled.

1 - saving of all images from a synchronous video camera is enabled.

Ulpr.NumberDetectedRestartTimeout

This key should be created if the LP recognition on one or more LPR channels stop from time to time. The key sets the time in minutes; if during this time no LPs were recognized, then the reaction is sent to the Intellect software core:

ULPR|N|NUMBER_DETECTED_TIMEOUT

where N is the identifier of the LPR channel object. Having received this reaction, the core re-sends the settings to the recognition module, thus emulating the Apply button click on the settings panel of the LPR channel object.

AutoInfo.Use

The key activates the display of the vehicle type in the Online Monitor window (if the Vehicle Type Recognition Module (UrlServer) is activated).

0 - the detected vehicle type is not displayed in the Online Monitor window.

1 - the detected vehicle type is displayed in the Online Monitor window.

AutoInfo.Url

http-address

http://127.0.0.1:8091/GetAutoInfo

The key sets the http-address for the interaction with the Vehicle Type Recognition Module (UrlServer).

The key sets the number of frames that are stored in the buffer for the Vehicle Type Recognition Module (UrlServer). It is defined as the approximate time spent by the vehicle in the frame multiplied by the fps of video.

If 0 - then the MMR (VIT) works.

If > 0 - then the Vehicle Type Recognition Module (UrlServer) works.

The key specifies the folder into which the frames processed by the Vehicle Type Recognition Module (UrlServer) will be saved (cropped frames containing only the vehicle). These frames are necessary for training a neural network.