Appendix: Video Feeds Properties

Supported Properties

Below is a list of all the supported video feed properties. UI Setting Name specifies the corresponding setting within the Desktop Client, and UI Setting Location specifies where the setting can be found in the Desktop Client.

Camera Properties

Property Default Value Description UI Setting Name UI Setting Location
input.back-channel.mobotix.cash-point “None” When the connected camera is a Mobotix camera, this property must be set to the configured cash point within the Mobotix app for the back-channel to work. Cash Point Camera Preferences menu
input.back-channel.type “None” When the connected camera is a Mobotix camera, you can set this property to “Mobotix MX” in order to have SAFR report STRANGER and RECOGNIZED event types to the camera. This feature is necessary if you want to make use of the Mobotix app. If the connected camera isn’t a Mobotix camera, this property doesn’t have any effect. Back Channel Camera Preferences menu
input.stream.url N/A The video stream URL. The URL must point to a RTSP, HTTP, or FILE stream. Address Camera Preferences menu
source N/A Source name. Source Camera Preferences menu

Detection Properties

Property Default Value Description UI Setting Name UI Setting Location
detector.detect-faces TRUE Whether detection of faces should be enabled for this feed. Enable face detector Face detector section of the Detection Preferences menu
detector.detect-faces-input-size “normal” Sets the face detector input size. This property allows you to manage the trade-off between accuracy vs. speed. There are 3 possible values:
normal - This is the standard against which the other 2 possible values are measured.
small - Decreased accuracy but increased speed.
large - Increased accuracy but decreased speed.
Input Size Face detector section of the Detection Preferences menu
detector.maximum-input-resolution 720 Maximum resolution of the Input image. Bigger images are scaled down (aspect-ratio preserving) to this resolution before detection. Reduce vertical input image size to Face detector section of the Detection Preferences menu
detector.minimum-required-face-size 0 The minimum size of faces to accept from the detector. Only faces with at least this size are eligible for recognition. Minimum required face size Face detector section of the Detection Preferences menu

Tracking Properties

Property Default Value Description UI Setting Name UI Setting Location
tracker.enable-face-bounds-prediction TRUE Enables face bounds prediction, which predicts which direction the face is moving to maintain tracking. Enable motion prediction Tracking Preferences menu
tracker.enable-face-size-correlation TRUE Enables face correlation of tracked faces, which compares detected faces looking for a change in area. Enable correlation of faces by size Tracking Preferences menu
tracker.failed-recognition-back-off-interval 340 After making the initial recognition attempts as quickly as possible, back up the amount specified by this setting for each subsequent recognition. This continues until the retry interval is reached. Failed recognition back-off interval Tracking Preferences menu
tracker.failed-recognition-retry-interval 0 The interval in which to run recognition requests if the face has not been recognized. Retry failed recognition after every Tracking Preferences menu
tracker.identity-relearn-interval-days 0 Updates the identity only when the currently saved identity is older than the updated identity. Relearn face interval days Tracking Preferences menu
tracker.identity-update-better-image FALSE Updates the identity when the currently saved identity is of lower quality (in all aspects) than the new image. Update identity with better image Tracking Preferences menu
tracker.initial-recognition-attempts 3 The number of initial recognition attempts to make on an unrecognized person as fast as possible. Initial recognition attempts Tracking Preferences menu
tracker.maximum-linger-frames 30 Determines for how many frames more we continue to keep a tracked face around after we have failed to detect it in the most recent frame. This makes the tracker resilient against intermittent loss of face. Stop tracking a face after it has lingered for Tracking Preferences menu
tracker.max-position-change-relative-to-face 115 The maximum position change, specified in percentage relative to the face size, to continue tracking. Maximum change to continue tracking, Face position Tracking Preferences menu
tracker.max-size-change-relative-to-face 50 The maximum size change, specified in percentage relative to the object size, to continue tracking. Maximum change to continue tracking, Size Tracking Preferences menu
tracker.min-failed-recognitions-to-stop-tracking-identity 3 When a face is being tracked recognitions are continually confirming the identity. The identity is also being verified if it is transferred from a person object. In these cases, if the recognition or verification fails this number of consecutive times then the identity will be reset and no longer associated with the face because we are no longer sure it is the same identity. Minimum failed recognitions to stop tracking identity Tracking Preferences menu
tracker.minimum-number-identical-recognitions-learn 2 The number of consecutive recognitions that need to occur before adding a new identity to the system. Minimum recognitions to learn identity Tracking Preferences menu
tracker.minimum-number-identical-recognitions-lock 1 The number of consecutive recognition attempts that we must run and produce the same person identity before we lock onto this identity. Minimum recognitions to lock on to identity Tracking Preferences menu
tracker.reconfirm-identity-in-video-on-every-key-frame FALSE When a key frame is encountered in a video file all the faces that are being tracked are marked as unconfirmed so that their identities are reconfirmed to make sure they are the same person. This setting only applies to video files; it can’t be used with live video. This property doesn’t actually appear in the VIRGO property list; possibly delete. Reconfirm identity in video after each Key Frame Tracking Preferences menu
tracker.reconfirmation-interval 1000 Identity reconfirmation time interval in ms. Reconfirm identity after every Tracking Preferences menu
tracker.stop-tracking-on-failed-re-recognition FALSE If recognition fails when re-recognizing a person then delete the identity that was created. Stop tracking on failed re-recognition Tracking Preferences menu

Recognition Properties

Property Default Value Description UI Setting Name UI Setting Location
recognizer.detect-age FALSE Enables the detection of age information. Age Detect section of the Recognition Preferences menu
recognizer.detect-gender FALSE Enables the detection of gender information. Gender Detect section of the Recognition Preferences menu
recognizer.detect-identity TRUE Enables detection of an identity, which matches against the existing database of people (identities). Identity Detect section of the Recognition Preferences menu
recognizer.detect-mask FALSE When enabled, SAFR will evaluate all occluded faces to see if they’re covered by a mask. If they are, then SAFR will use the mask enhanced model to attempt to recognize the face behind the mask. If the occluded face isn’t covered by a mask, then the normal occluded model will be used instead. Mask Detect section of the Recognition Preferences menu
recognizer.detect-mask-threshold 0.5 Specifies the threshold at and above which mask detection will conclude that mask=true. Mask Detection Threshold Detect section of the Recognition Preferences menu
recognizer.detect-occlusion FALSE Enables occlusion detection during recognition. Occlusion Detect section of the Recognition Preferences menu
recognizer.detect-sentiment FALSE Enables the detection of sentiment information. Sentiment Detect section of the Recognition Preferences menu
recognizer.identity-masked-threshold-offset 0 Sets the identity threshold when detecting masks. Masked face threshold offset Identity recognition threshold section of the Recognition Preferences menu
recognizer.identity-proximity-threshold-allowance 0.13 A boost value that is added to the Identity Recognition Threshold. Proximity threshold allowance Identity recognition threshold section of the Recognition Preferences menu
recognizer.identity-recognition-threshold 0.54 Identity recognition threshold. Identity recognition threshold Identity recognition threshold section of the Recognition Preferences menu
recognizer.learning-enabled FALSE Enables the feed to learn new identities. Identity Detect section of the Recognition Preferences menu
recognizer.learn-occluded-faces FALSE Enables learning of occluded faces regardless of the maximum occlusion setting. If this is true then the server configuration will be used, which by default doesn’t do any occlusion detection. Allow learning of occluded faces Detect section of the Recognition Preferences menu
recognizer.maximum-clip-ratio 0.1 The maximum clip ratio on either side the recognition candidate might have. For recognition Clipping tolerances section of the Recognition Preferences menu
recognizer.maximum-clip-ratio-identification 0 The maximum clip ratio on either side the insertion candidate might have. For learning/strangers Clipping tolerances section of the Recognition Preferences menu
recognizer.maximum-occlusion 0 The maximum occlusion value that is allowed when adding new candidate images into the Person Directory. If the face is occluded with a value greater than this then the face will not be added, but if it’s less than or equal to this value then it will be added. Occlusion threshold Detect section of the Recognition Preferences menu
recognizer.maximum-pitch-identification 0.4 The maximum pitch value used to determine if the face is looking straight ahead. The pitch value is the forward/backward movement of the face. Max Pitch Minimum required center pose quality section of the Recognition Preferences menu
recognizer.maximum-roll-identification 0.15 The maximum roll value used to determine if the face is looking straight ahead. The roll value is the side to side tilt movement of the face. Max Roll Minimum required center pose quality section of the Recognition Preferences menu
recognizer.maximum-yaw-identification 0.4 The maximum yaw value used to determine if the face is looking straight ahead. The yaw value is the side to side movement of the face. Max Yaw Minimum required center pose quality section of the Recognition Preferences menu
recognizer.minimum-center-pose-quality 0.05 The minimum center pose quality that a recognition candidate must have in order to allow the addition of the candidate image into the Person Directory. For recognition Minimum required center pose quality section of the Recognition Preferences menu
recognizer.minimum-center-pose-quality-identification 0.45 The minimum center pose quality that a recognition candidate must have in order to allow the addition of the candidate image into the Person Directory. For learning/strangers Minimum required center pose quality section of the Recognition Preferences menu
recognizer.minimum-center-pose-quality-merging 0.59 The minimum center pose quality that a recognition candidate must have in order to allow merging. For merging Minimum required center pose quality section of the Recognition Preferences menu
recognizer.minimum-face-contrast-quality 0.1 The minimum face contrast quality that a face image must have before recognition is attempted. For recognition Minimum required face contrast quality section of the Recognition Preferences menu
recognizer.minimum-face-contrast-quality-identification 0.3 The minimum face contrast quality that a recognition candidate must have in order to allow the addition of the candidate image into the Person Directory. For learning/strangers Minimum required face contrast quality section of the Recognition Preferences menu
recognizer.minimum-face-contrast-quality-merging 0.45 The minimum face contrast quality that a recognition candidate must have in order to allow merging. For merging Minimum required face contrast quality section of the Recognition Preferences menu
recognizer.minimum-face-sharpness-quality 0.1 The minimum face sharpness quality that a face image must have before recognition is attempted. For recognition Minimum required face sharpness quality section of the Recognition Preferences menu
recognizer.minimum-face-sharpness-quality-identification 0.3 The minimum face sharpness quality that a recognition candidate must have in order to allow the addition of the candidate image into the Person Directory. For learning/strangers Minimum required face sharpness quality section of the Recognition Preferences menu
recognizer.minimum-face-sharpness-quality-merging 0.45 The minimum face sharpness quality that a recognition candidate must have in order to allow merging. For merging Minimum required face sharpness quality section of the Recognition Preferences menu
recognizer.minimum-face-size 80 The minimum size of faces to detect. This value is applied after searching the image. For recognition Minimum required face size section of the Recognition Preferences menu
recognizer.minimum-face-size-identification 120 The minimum resolution that a recognition candidate image must have in order to allow the addition of the candidate image into the Person Directory. For learning/strangers Minimum required face size section of the Recognition Preferences menu
recognizer.minimum-face-size-merging 220 The minimum resolution a recognition candidate must have in order to allow merging. For merging Minimum required face size section of the Recognition Preferences menu
recognizer.pose-configuration-identification-enabled FALSE If this is true then pose configuration is enabled for identification. The pose configuration allows for replacing center pose quality with advanced parameters such as yaw, pitch and roll. When pose configuration is enabled, then recognizer.minimum-center-pose-quality is ignored and the following 3 properties are used instead: recognizer.maximum-yaw-identification, recognizer.maximum-pitch-identification, and recognizer.maximum-roll-identification. Identification Enabled Pose liveness action configuation section of the Recognition Preferences menu

Event Properties

Property Default Value Description UI Setting Name UI Setting Location
reporter.delay 0 Delay the event reporting to the server by this amount in seconds. Reporting delay Report events section of the Events Preferences menu
reporter.enabled TRUE Enables or disables event reporting. Report events Report events section of the Events Preferences menu
reporter.maximum-face-image-size 240 When event images are being saved, this property specifies the maximum size of the event face images, in pixels. Preserve Event Face Image, Max Image Size Report events section of the Events Preferences menu
reporter.maximum-scene-image-size 320 When event scene thumbnail images are being saved, this property specifies the maximum size of the event scene thumbnail images, in pixels. Preserve Event Scene Thumbnail Image, Max Image Size Report events section of the Events Preferences menu
reporter.minimum-event-duration-identified 0 The minimum allowed recognized person event duration in seconds. Events shorter than this duration will not be reported. Min Identified Event Duration Report events section of the Events Preferences menu
reporter.minimum-event-duration-stranger 0 The minimum allowed stranger event duration in seconds. Events shorter than this duration will not be reported. Min Stranger Event Duration Report events section of the Events Preferences menu
reporter.minimum-event-duration-unidentified 1500 The minimum allowed unrecognizable person event duration in seconds. Events shorter than this duration will not be reported. Min Unrecognizable Event Duration Report events section of the Events Preferences menu
reporter.report-event-face TRUE Enables the inclusion of face thumbnails in event reports. Preserve Event Face Image Report events section of the Events Preferences menu
reporter.report-event-scene FALSE Enables the inclusion of scene images in event reports. Preserve Event Scene Thumbnail Image Report events section of the Events Preferences menu
reporter.report-secondary-events FALSE Reports secondary events. Secondary events are events that are associated with a primary event via the rootEventId property in the event. It is usually preferred to only report the primary events and the secondary events need to only be reported if there is more detail needed. If this is disabled then all events with a rootEventId property set to a primary event will not be reported. Only events with rootEventId not set to anything will be reported, which are the primary events. Include Secondary Events Report events section of the Events Preferences menu
reporter.report-speculated-events TRUE Reports events for speculated faces. Speculated faces are faces that aren’t a 100% match, but are close. Include Speculated Identity Events Report events section of the Events Preferences menu
reporter.report-stranger-events TRUE Reports events for people that are strangers. These are people not registered by the system after running facial recognition on the face. Include Stranger Events Report events section of the Events Preferences menu
reporter.report-unrecognizable-events TRUE Reports events for people that are not recognizable. Include Unrecognizable Events from Camera and Include Unrecognizable Events from Video Report events section of the Events Preferences menu
reporter.stranger-events.only-if-occluded FALSE Specifies whether only occluded stranger events should be reported. By default stranger events are only generated if the face is not occluded, if occlusion detection is enabled, otherwise they are generated when the face meets the identification image quality metrics. If this option is set to true then stranger events will be reported only if the face is occluded. Include Stranger Events, Only if occluded Report events section of the Events Preferences menu
reporter.stranger-maximum-age 0 The maximum age of strangers that will trigger stranger events. If a stranger older than the specified maximum age is detected, no stranger event is generated. Include Stranger Events, Max Age Report events section of the Events Preferences menu
reporter.stranger-minimum-age 0 The minimum age of strangers that will trigger stranger events. If a stranger younger than the specified minimum age is detected, no stranger event is generated. Include Stranger Events, Min Age Report events section of the Events Preferences menu
reporter.update-images FALSE Updates the thumbnail images with higher quality images during the course of the event if possible. Update in-progress event attributes, Include qualified images with updates Report events section of the Events Preferences menu
reporter.update-in-progress-event-interval 1000 When reporter.update-in-progress-event-properties is set to TRUE, this property specifies the time interval in which to update event properties that change. When reporter.update-in-progress-event-properties is set to FALSE, this property has no effect. Update in-progress event attributes, Update interval Report events section of the Events Preferences menu
reporter.update-in-progress-event-properties FALSE If this is enabled, then any event properties that change will be updated at the specified reporter.update-in-progress-event-interval. Many properties do change periodically. (e.g. averages that are continually computed) Update in-progress event attributes Report events section of the Events Preferences menu

Miscellaneous Properties

Property Default Value Description UI Setting Name UI Setting Location
directory N/A Directory name. User Directory Account Preferences menu
mode “Enrolled and Stranger Monitoring” Specifies which video processing mode the feed is using. The Video Processing Mode drop-down menu Camera Feed Analyzer
reporter.events-initial-date-offset 0 When processing a video file for events this value can be used to set the initial date offset to use for the events being processed. By default video events start with current system time.
site N/A Site name, if any. Default Site Account Preferences menu

Properties Not Appearing in the UI

Property Default Value Description
enabled FALSE Enables or disables the feed.
input.type “stream” The type of feed input; either “stream” or “file”.
recognizer.detect-mask-model “precise” Specifies the model to be used for mask detection. There are 3 possible values:
Precise: This model produces the least number of false positives (i.e. detecting that a person is wearing a mask but there is no mask), but it suffers from the lowest true positive rate. (i.e. detecting masks that are actually there)
Sensitive: This model produces the highest true positive rate, but it suffers from the highest number of false positives.
Normal: This model produces a moderate amount of both false positives and true positives.
recognizer.mask-check-detection-edge-threshold 0.03 How far a face must be from the edge of the screen before a mask event detection is attempted. For example, if a face is 100 pixels, and recognizer.mask-check-detection-edge-threshold is set to .03 (i.e. 3%), then the face must be 3 pixels from the edge of the screen before SAFR will attempt a mask event detection. This property is not supported by SAFR Inside.
recognizer.mask-check-enabled FALSE Enables the detection of mask event types. Mask event detection attempts can return 3 potential results: mask=false, mask=indeterminate, or mask=true. After the configured number of consecutive mask event detection results, the mask event state is set to the appropriate value. The mask event state can only progress from false towards true; the state never regresses back towards false. For example, once the mask event state for a viewed person becomes set to mask=true, then that person’s mask event state won’t ever regress to mask=indeterminate or mask=false.
Events are generated when the mask event state is set to either mask=false or mask=true.
recognizer.mask-check-min-consecutive-mask-detections 1 Specifies the minimum number of consecutive mask=true mask detection results that must occur before SAFR will generate a mask=true event. See the recognizer.mask-check-enabled property for more information.
recognizer.mask-check-min-consecutive-no-mask-detections 2 Specifies the minimum number of consecutive mask=false mask detection results that must occur before SAFR will generate a mask=false event. See the recognizer.mask-check-enabled property for more information.
recognizer.mask-check-min-consecutive-occluded-no-mask-detections 2 Specifies the minimum number of consecutive mask=indeterminate mask detection results that must occur before SAFR will set the mask event state to mask=indeterminate. See the recognizer.mask-check-enabled property for more information.
recognizer.mask-check-min-mask-detection-size 70 The smallest face size, in pixels, upon which SAFR will attempt to detect a mask event.
statistics.enabled FALSE Specifies whether VIRGO should record and report statistics for this feed.

Unsupported Properties

The following video feed properties are implemented for Video Recognition Gateway (VIRGO) feeds, but aren’t supported for SAFR Inside.

See Also