Go to documentation repository
Page History
...
FACE Intellect | |||||
|---|---|---|---|---|---|
Registry section | String parameter | Available values | Default | Product version | Parameter in effect |
x32: (x32)\FRS | CpuCoreCount | >0 | 6.0 | The key defines on how many CPU cores the face recognition module will operate (firserver.run process). All cores are in use by default. | |
| x32: (x32)\FRS x64: (x64)\FRS | FaceLostAge | >0 | 1000 | 6.0 | The key sets the timeout upon which Face Server ‘loses’ the face if there is no new data about it. |
| x32: (x32)\FRS x64: (x64)\FRS | GenFirsInDetector | 0, 1 | 1 | 6.0 | 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. Generation of biometrics is a resource-intensive process unlike search by ready data - that is why this key allows distributing load among several Servers having only one Server working with the user database. |
| x32: (x32)\FRS x64: (x64)\FRS | SaveUnrecognizedFaces | 0, 1 | 0 | 6.0 to 6.1 | Specifies what data will be stored in the database when using the Face recognition Server: 1 - all captured faces. 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. |
| x32: (x32)\Video\FaceCapture x64: (x64)\Video\ FaceCapture | timeUntilLost | >0 | 1 | Intellect 4.10.0 | 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. If the parameter value is 3, then the face will be detected in this case. |
| x32: (x32)\FRS x64: (x64)\FRS | IgnoreSamePeople | 0, 1 | 0 | 6.1 | The key enables function of ignoring repeatedly recognized faces. While enabling this function all vectors of captured faces are saved in cache for the specified time interval. When new face is captured, its biometric vector is comparing with already existed vectors in cache. If it coincides with one of such vectors with specified similarity rate then it doesn't send to the further processing. Duration of vector storing in a cache is specified using the Skip repeated recognitions, sec parameter of the Face Recognition Server object. Similarity rate for comparison is came from the Similarity level parameter of the same object. See also Face Intellect software package. Administrator's Guide, section Setting parameters for detected faces recognition. |
| x32: (x32)\FRS x64: (x64)\FRS | ClearIgnoreCache | 0, 1 | 0 | 6.1 | The key enables cache clearing while using function of ignoring repeatedly recognized faces. |
| x32: (x32)\FRS x64: (x64)\FRS | ClearIgnoreCacheTime | Time in HH:MM:SS format | - | 6.1 | The key sets time when cache crearing is to be performed while using function of ignoring repeatedly recognized faces. |
| x32: (x32)\FRS x64: (x64)\FRS | FaceDetectionPeriod | >0 | 250 | 6.1 | Specifies time period in milliseconds equal to frequency of new faces search on the image for the Tevian recognition algorithm. See also Face Intellect software package. Administrator's Guide. |
| x32: (x32)\FRS x64: (x64)\FRS | FaceDB | Full path to a local or network folder | - | 7.0 | The key sets a folder for storage of images and vectors for captured and sample faces when UseFaceDB key is set to 1 or 2 (see below). |
| x32: (x32)\FRS x64: (x64)\FRS | UseFaceDB | 0, 1, 2 | 2 | 7.0 | 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). Note. Information on recognized faces is stored in the database, regardless of the value of the UseFaceDB key.Images of reference faces are always stored in the <Installation directory Intellect> \ Bmp \ Person folder, regardless of the value of the UseFaceDB key. |
| x32: (x32)\FRS x64: (x64)\FRS | FaceDBFreeMB | >0 | 1000 | 7.0 | The key is used if the the UseFaceDB parameter value is 1 or 2 (see above). The key specifies free space in the disk volume in megabytes. Once the specified size is reached, the images and captured face vectors cleanup will start on loop. |
| x32: (x32)\FRS x64: (x64)\FRS | RestPort | port number | 10000 | 7.1 | The key is used in case the standard port 10000 used by the Face Recognition Server to communicate with the Face Recognition and Search client is occupied by a third-party application that can not be disabled. The key allows you to specify a new port number for communication between the server and the client. |
| х32: (х32)\FRS x64: (х64)\FRS | CpuCoreCountAddPerson | >=0 | 0 | 7.1 | 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. etc. |
| х32: (х32)\FRS x64: (х64)\FRS | Face.HardwareCPU | 0, 1, 2 | - | 7.1 | 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. |
| х32: (х32)\FRS x64: (х64)\FRS | Face.RecognizeFacesSeparately | 0, 1 | 0 | 7.2 and later | 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. |
| х32: (х32)\FRS x64: (х64)\FRS | FaceDetector.SaveLastFaceCaptureFrame | 0, 1 | 0 | 7.1 and later | 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. |
| х32: (х32)\FRS x64: (х64)\FRS | XSize | >=0 | 1920 | 7.0 and later | 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". |
| х32: (х32)\FRS x64: (х64)\FRS | YSize | >=0 | 1080 | 7.0 and later | The key restricts resolution (height) 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". |
| Tevian | |||||
| х32: (х32)\FRS x64: (х64)\FRS | TevianAlgorithmNumber | 0, 1 | 0 | 7.0-7.1 | 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. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.DetectionFilterAlgorithm | 0, 1 | 0 | 7.2 and later | Another filtering false events algorithm. 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. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.DetectionFilterValue | 0-100 | 50 | 7.2 and later | Configuring alternative algorithm filtering. It is in use if the value of Tevian.GlobalTrackingDetectionFilter if more than 0 (see the corresponding parameter below). Note. It is not recommended to change this parameter without consulting Tevian. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.DetectorAlgorithm | 0, 1 | 0 | 7.2 and later | 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. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.FaceDetectionPeriod | >=0 | 350 | 7.2 and later | 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. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.FaceDetectorConfidenceThreshold | >=0 | 50 | 7.2 and later | Face detector confidence threshold (do not confuse with face quality). Note. It is not recommended to change this parameter without consulting Tevian. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.GlobalTrackingDetectionFilter | 0, 1 | 0 | 7.2 and later | Filtering false events in the tracker (IGlobalTracker). 0 - disabled 1 - enabled Note. It is not recommended to change this parameter without consulting Tevian. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.IdentificationAlgorithm | 0, 1 | 0 | 7.2 and later | The key enables selecting the Tevian algorithm. 0 - ALG1 less resource intensive algorithm is in use. 1 - ALG2 identification of the highest quality, but more resource intensive. 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. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.TrackBestFramesCount | >=0 | 1 | 7.2 and later | 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. 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. |
| х32: (х32)\FRS\CustomAlgoritm x64: (х64)\FRS\CustomAlgoritm | Tevian.TrackerMaxLostTime | >=0 | 500 | 7.2 and later | Time since the last recognition after which the track is considered ended. Note. It is not recommended to change this parameter without consulting Tevian. |
| х32: (х32)\FRS x64: (х64)\FRS | FaceTracker.LogTrackerQuality | 0, 1 | 0 | 7.2 and later | The key enables logging of every face capture event in the general log file of the Face Recognition Server debugging window, where additional information is displayed, such as: the quality of the captured face, the number of all captured faces, the number of high-quality faces, etc. (for details, see Appendix 2. Debug window). |
AUTO Intellect | |||||
Registry section | String parameter | Available values | Default | Product version | Parameter in effect |
x32: (x32)\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 | 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 | WriteSpeedOnTitles | 0, 1 | 0 | 4.7.5 and later | Defines whether to write speed values on titles. |
x32: (x32)\URMLPR | DisableUrmOutput | 0, 1 | 0 | 4.7.5 and later | Disables results output. |
x32: (x32)\URMLPR | GlobalUrmDebug | 0, 1 | 0 | 4.7.5 and later | Enables displaying CZoneInfo objects in dbgview. |
x32: (x32)\URMLPR | OneSpeedDetect | 0, 1 | 0 | 4.7.5 and later | Enables filtering the radar speed values. |
x32: (x32)\URMLPR | ReadSpeedFromTitles | 0, 1 | 0 | 4.7.5 and later | Defines whether to read speed from titles or not. |
x32: (x32)\URMLPR | TestWidth | - | 0 | 4.7.5 and later | Image width change (internal use only). |
x32: (x32)\URMLPR | TestHeight | - | 0 | 4.7.5 and later | Image height change (internal use only). |
x32: (x32)\URMLPR | Time | - | - | 4.7.5 and later | Saves time of the last viewed archive fragment in the test mode. |
x32: (x32)\URMLPR | UrmDebug | 0, 1 | 0 | 4.7.5 and later | Enables recording of tiff files to UrmDebug folder. |
x32: (x32)\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 | UseTry | 0, 1 | 0 | 4.7.5 and later | Enables the seh module. |
x32: (x32)\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 | CountryName | Text | RUS | 4.7.5 and later | Sets the test country name. |
x32: (x32)\URMLPR\UnitTest | Enabled | 0, 1 | 0 | 4.7.5 and later | Enables/disables test. |
x32: (x32)\URMLPR\UnitTest | ExecuteSecond | > = 0 | 3 | 4.7.5 and later | Sets time of test execution. |
x32: (x32)\URMLPR\UnitTest | Number | Text | M038EH150 | 4.7.5 and later | Sets the test number. |
x32: (x32)\URMLPR\UnitTest | PlateHeightPercent | > 0 | 15 | 4.7.5 and later | Sets the test license plate height. |
x32: (x32)\URMLPR\UnitTest | PlateWidthPercent | > 0 | 25 | 4.7.5 and later | Sets the test license plate width. |
x32: (x32)\URMLPR | ParkingMode | 0, 1 | - | 5.0 | Enabling the parking mode for 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. |
x32: (x32)\URMLPR | SaveRawRecognitionResult | 0,1 | 0 | 5.1 | When value = 1, the key allows saving frames transmitted from Intellect to the CARMEN Parking / CARMEN-Auto module.
When value = 1, frames are not saved. |
x32: (x32)\URMLPR | TrackOnlyRedLight | 0, 1 | 1 | 5.1 | When value = 1, the key allows fixing violations by the traffic violations detection (crossing the stop line, stop over crosswalk line, running a red light) only for vehicles which crossed the stop line on red light. |
x32: (x32)\URMLPR | MaxStoppingSpeed | 0 - 10000 | 1000 | 5.1 | Controls maximal speed in relative units (relatively from width and height of frame) at which the vehicle is still considered as the stopped vehicle (for the Stop over crosswalk line violation). |
x32: (x32)\URMLPR | RayHardwareDelay | >0 | 0 | 5.2 | Sets time (in milliseconds) corresponding to the delay with which events about green/red traffic lights are received. Example. If the key value is RayHardwareDelay=2000 and an event is received at 12:00:00, then the system thinks the event is received at 11:59:58. |
x32: (x32)\URMLPR | TimestampFontSize | >=139 | 139 | 5.2 | The key sets the text font size on the photo of the fine (containing date and time). The value is font size multiplied by 10. For instance, if the key is 139, then the font size will be 13,9pnt. |
x32: (x32)\URMLPR | ReadRayFromTitles | 0, 1 | 0 | 5.3 | 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). 1 – information about the time when the license plates recognition is to be started is taken from the titles overlaid on the video. |
x32: (x32)\URMLPR | PlateImprover | 0, 1, 2 | 0 | 5.3 | 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. |
| 0, 1, 2, 3 | 5.4 | ||||
x32: (x32)\URMLPR | SpeedField | "FASTEST", "STRONGEST" | "FASTEST" | 5.4 | "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 | Compress | 0, 1 | 1 | 5.2 | The parameter is intended for disabling compression when transferring video from the video subsystem (the Camera object) to the LPR channel, if the video subsystem and the LPR channel are on the same local computer. This allows reducing the load on the Server processor. 0 – the video is transmitted to the local LPR channel without compression. 1 – the video is transmitted to the LPR channel after compression. |
x32: (x32)\URMLPR | RemoteLpr.NearestTime | Full path to local or network folder | 0 | 5.3 | 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. |
| х32: (х32)\URMLPR x64:(х64)\URMLPR | LprDB.Path | 0, 1 | C:\ProgramData\AxxonSoft\LprDB | 5.5 | Specifies the local or network folder for storing the recognized LP images and vehicle images if the LprDB.Use key value 1 (see below) is specified. |
| х32: (х32)\URMLPR x64:(х64)\URMLPR | LprDB.Use | 0, 1 | 1 | 5.5 | 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. |
| х32: (х32)\URMLPR x64:(х64)\URMLPR | LprDB.FreeMB | >0 | 5000 | 5.5 | 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). |
| х32: (х32)\URMLPR x64: (х64)\URMLPR | Alarms.LimitedByBestResult | 0, 1 | 0 | 5.5 | The parameter allows ignoring all the tracks after the best frame detected by SDK. 0 - tracks after the best frame detected by SDK are not ignored. 1 - all the tracks after the best frame detected by SDK are ignored. |
| х32: (х32)\URMLPR x64: (х64)\URMLPR | Alarms.CrossWalkOne | 0, 1 | 0 | 5.5 | The parameter activates alarm even if only one plate is recognized at the crosswalk (regardless of if the vehicle was moving or not). 0 - the system tries to detect crossing the crosswalk and only after that activates alarm. 1 - activates alarm even if only one plate is recognized at the crosswalk. |
| х32: (х32)\URMLPR x64:(х64)\URMLPR | SaveRecognitionResult | 0, 1 | 0 | 5.5 | Activates saving the recognition results to the hard drive. It is used for the Traffic violations detection module debugging. 0 - the recognition results are saved to the Auto Intellect DB. 1 - the recognition results are saved to the hard drive. |
| х32: (х32)\URMLPR x64: (х64)\URMLPR | AutoUragan.SDKVersion | 3.5, 3.7 | 3.5 | 5.5 and later | The key sets the SDK version which is being used in the Auto-Uragan software module. |
Detectors pack | |||||
|---|---|---|---|---|---|
Registry section | String parameter | Available values | Default | Product version | Parameter in effect |
x32: (x32)\DetectorExt\HeatZoneDetector x64: (x64)\DetectorExt\HeatZoneDetector | ReportFrequency | >0 | 900 | 4.9.0 and later | Sets the data collection frequency (sec) for heat zone detection tool. |
x32: (x32)\DetectorExt\HeatZoneDetector x64: (x64)\DetectorExt\HeatZoneDetector | DebugReportFrequency | >0 | 10 | 4.9.0 and later | Sets the data update frequency (sec) from heat zone detection tool in the Debug window in seconds. |
| х32: (X32)\Video\ x64: (x64)\Video\ | report_frequency | >=0 | 3000 | 2.6 and later | Sets the time period in milliseconds, during which the repeated triggering of the Sweethearting detection module is ignored. |
Overview
Content Tools