Cameras

The Cameras dashboard in the SmartFace Station is your command center for registering cameras and edge streams, access a detailed list of your devices, and effortlessly configure and manage them to meet your surveillance requirements.

Cameras dashboard

Camera Dashboard Sections

The cameras dashboard contains several sections:

  1. Title bar
  2. Selected filter area
  3. Camera and edge stream list
  4. Fulltext search
  5. Available filters

Cameras dashboard - section

Title bar

At the top of the page, you’ll find the Title Bar, which displays the name of the page - Cameras, helping you quickly identify your location within the SmartFace Station interface. Next to the dashboard name, the number of registered cameras and edge streams is displayed.

Title bar of the Cameras page

Selected filter area

Directly below the Title Bar, you’ll encounter the Selected Filter Area, but it is only visible when a filter has been applied. This section allows you to refine the camera and edge stream list by applying specific filters, customizing the displayed content according to your preferences.

Selected filters

Camera and edge stream list

The central part of the dashboard is dedicated to listing all registered cameras and edge streams. This comprehensive list provides a visual overview of your surveillance devices, making it easy to identify and access each one.

Cameras and edge streams list

To facilitate efficient device lookup, the Full-Text Search feature is available. This allows you to quickly search for specific cameras or edge streams by entering keywords or names.

Full-text search

Available filters

In addition to the Selected Filter Area, you’ll also have access to a list of Available Filters. These filters can help you further refine and categorize the devices in the camera and edge stream list based on source type and status.

Available filters

Camera management

In this part of the documentation you will explore how to effectively managing cameras within the SmartFace Station. Camera management encompasses a range of essential activities, including:

Set up new camera

The SmartFace Station allows you to register a RTSP camera in the SmartFace Platform. When registering the camera, you can set its name and configure the video source. To do so, follow these steps:

  1. Click on Cameras in the left menu panel.
  2. Click on ADD CAMERA button on the right side of the dashboard.
  3. Enter the Name and RTSP / Video source.
  4. To register a new camera, click on ADD CAMERA button.

⚠️ Please note that you may register only as many cameras as you have registered camera services on SmartFace Platform server.

Enable/Disable camera

When you enable a camera in the SmartFace Station, SmartFace Platform will start to process the video stream from the camera and the SmartFace Station will start to display notifications and successful passages. For more information about the settings, see camera sonfiguration.

To enable or disable a registered camera in the SmartFace Station:

  1. Click on Cameras in the left menu panel.
  2. Open Camera configuration by clicking on item in camera list.
  3. You may either:
    • Enable the camera, by switching on the toggle button Enabled (appears green).
    • Disable the camera, by switching off the toggle button Enabled (appears red).

Enabled camera

Disabled camera

Configure camera

The SmartFace Station allows you to configure cameras. These settings directly impact the processing of video streams by the SmartFace Platform.

To modify the camera configuration:

  1. Click on Cameras in the left menu panel.
  2. Open Camera configuration by clicking on item in camera list.
  3. Now, you can modify camera name and camera configuration parameters.

Camera configuration parameters

Parameter nameDescriptionDefault valueValue interval
General
CAMERA NAMEThe name of camera
RTSP / VIDEO SOURCEA RTSP URL to the camera stream or video file name with full path for file location
OS SERVICE NAMEThe camera service name. It is read only information,<assigned by the system>
Face detection
FACE DETECTOR RESOURCEChoose between these resources for detection:

  • None - no face detection enabled
  • CPU - face detection using NN with balanced mix of speed vs. accuracy, performed directly in the camera process on CPU
  • CPU Remote - face detection using NN with balanced mix of speed vs. accuracy, performed remotely in Detector process on CPU
  • Accurate CPU - face detection using NN that is more accurate but slower, performed directly in the camera process on CPU
  • Accurate CPU remote - face detection using NN that is more accurate but slower, performed remotely in Detector process on CPU
  • GPU - face detection using NN with balanced mix of speed vs. accuracy, performed directly in the camera process on GPU
  • GPU Remote - face detection using NN with balanced mix of speed vs. accuracy, performed remotely in detector process on GPU
  • Accurate GPU - face detection using NN that is more accurate but slower, performed directly in the camera process on GPU
  • Accurate GPU remote - face detection using NN that is more accurate but slower, performed remotely in detector process on GPU
  • Any Remote - face detection using NN with balanced mix of speed vs. accuracy, performed remotely in detector process on any resource (GPU or CPU) according to their current utilization.
  • Accurate Any remote - face detection using NN that is more accurate but slower, performed remotely in detector process on any resource (GPU or CPU) according to their current utilization.

CPU
CONFIDENCE THRESHOLDThe confidence threshold for face detection450
MIN FACE SIZEThe minimum face size necessary for detection in pixels35
MAX FACE SIZEThe maximum face size necessary for detection in pixels600
MAX FACESThe maximum number of faces detected on one frame
⚠️Setup this value according to your use-case. Lowering this number, you can significantly decrease overall detection speed.
20
FACE DISCOVERY FREQUENCYThe frequency of face detection in milliseconds500
FACE SAVE STRATEGY

The strategy for saving data from all detections, you can choose from:

  • All- All faces for the detected person are stored.
  • FirstFace - Only the first detected face of a person is stored.
  • BestFace - Only the best face for the detected person is stored. Which face is the best is decided when the person is lost from tracking.
  • FirstFace, BestFace - The first and the best face for the detected person are stored.
  • MatchedOnly - Only faces which are matched against a watchlist member are stored.

⚠️Set this wisely. Strategy to save all detected objects can generate huge amount of data.

BestFace
Face extraxtion
TEMPLATE GENERATOR RESOURCEChoose between these resources for template extraction:

  • CPU - to perform the template extraction on CPU resource.
  • GPU - to perform the template extraction on GPU resource. GPU must be present in the system.
  • ANY - to perform the template extraction on any resource (GPU or CPU) according to their current utilization. GPU must be present in the system.

CPU
FACE EXTRACTION FREQUENCYThe frequency of face extraction in milliseconds500
Pedestrian detection
PEDESTRIAN DETECTOR RESOURCE

Turn on pedestrian detection on selected camera. Choose which detector will be used for pedestrian detection.

You can choose from:

  • None - no pedestrian detection enabled
  • CPU Remote - use special Innovatrics NN to perform the detection on CPU
  • GPU Remote - use special Innovatrics NN to perform the detection on GPU. GPU must be present in the system.
  • Any Remote - use special Innovatrics NN to perform the detection on any resource (GPU or CPU) according to their current utilization. GPU must be present in the system.
  • SFE CPU Remote - performs the detection on CPU. It is effective if object detection is turned on at the same time.
  • SFE GPU Remote - performs the detection on GPU. It is effective if object detection is turned on at the same time.
  • SFE Any Remote - performs the detection on any resource (GPU or CPU) according to their current utilization. GPU must be present in the system. It is effective if object detection is turned on at the same time.
  • BodyParts - use body-parts (CPU) detector to determine where is the pedestrian is located on image

None
CONFIDENCE THRESHOLDThe confidence threshold for pedestrian detection2 5000 ↔︎ 10 000
MIN PEDESTRIAN SIZEThe minimum pedestrian size necessary for detection in pixels8020 ↔︎ 10 000
MAX PEDESTRIAN SIZEThe maximum pedestrian size necessary for detection in pixels2 00021 ↔︎ 10 000
MAX PEDESTRIANSThe maximum number of pedestrians detected on one frame201 ↔︎ 1 000
PEDESTRIAN SAVE STRATEGY

The strategy for saving data from all detections, you can choose from:

  • All - All information regarding to the detected pedestrian are stored.
  • Best - Only information pertaining to the pedestrian in the tracklet with the highest quality level is stored. Which pedestrian of the detected person is the best is decided when the person is lost from tracking.

⚠️Set this wisely. Strategy to save all detected objects can generate huge amount of data.

Best
Pedestrian attributes extraction
PEDESTRIAN ATTRIBUTES EXTRACTORE RESOURCE

Turn on enhanced pedestrian attributes on selected camera. Choose which extractor will be used for pedestrian attributes extraction.

You can choose from:

  • None - no pedestrian attributes extraction enabled
  • CPU - use special Innovatrics NN to perform the detection on CPU
  • GPU - use special Innovatrics NN to perform the detection on GPU. GPU must be present in the system.
  • Any - use special Innovatrics NN to perform the detection on any resource (GPU or CPU) according to their current utilization. GPU must be present in the system

None
Object detection
OBJECT DETECTOR RESOURCE

Turn on object detection on selected camera. Choose which detector will be used for object detection.

You can choose from:

  • None - no object detection enabled
  • CPU Remote - use special Innovatrics NN to perform the detection on CPU
  • GPU Remote - use special Innovatrics NN to perform the detection on GPU. GPU must be present in the system.
  • Any Remote - use special Innovatrics NN to perform the detection on any resource (GPU or CPU) according to their current utilization. GPU must be present in the system.

⚠️To enable object detection, you must ensure that at least one object from the Object Type parameter is selected.

None
CONFIDENCE THRESHOLDThe confidence threshold for object detection5 0000 ↔︎ 10 000
MIN OBJECT SIZEThe minimum object size necessary for detection in pixels8020 ↔︎ 10 000
MAX OBJECT SIZEThe maximum object size necessary for detection in pixels2 00021 ↔︎ 10 000
MAX OBJECTSThe maximum number of objects detected on one frame201 ↔︎ 1 000
OBJECT SAVE STRATEGY

The strategy for saving data from all detections, you can choose from:

  • All - All information regarding to the detected object are stored.
  • Best - Only information pertaining to the object in the tracklet with the highest quality level is stored. Which object of the detected object is the best is decided when the object is lost from tracking.

⚠️Set this wisely. Strategy to save all detected objects can generate huge amount of data.

Best
OBJECT TYPE

You can choose which objects will be detected on the camera

You can choose from three categories:

  • Vehicles: Car, Bus, Truck, Motorcycle, Bicycle, Boat, Airplane, Train.
  • Animals: Bird, Cat, Dog, Horse, Sheep, Cow, Bear, Elephant, Giraffe, Zebra.
  • Other objects: Suitcase, Backpack, Handbag, Umbrella, Knife.

Spoof detection
DISTANT DETECTOR RESOURCE

Choose liveness approach for spoof detector.

You can choose from:

  • None - no spoof detection enabled
  • Distant CPU - NN based liveness for access control use-case executed on CPU
  • Distant GPU - NN based liveness for access control use-case executed on GPU
  • Distant ANY - NN based liveness for access control use-case executed on any resource (GPU or CPU) according to their current utilization.

DISTANT LIVENESS SCORE THRESHOLDAnything below this value from distant liveness check will be considered as spoof.
Available only for Distant CPU and Distant GPU spoof detector resource
900 ↔︎ 100
NEARBY DETECTOR RESOURCE

Choose liveness approach for spoof detector.

You can choose from:

  • None - no spoof detection enabled
  • Nearby CPU - NN based liveness for selfie use-case executed on CPU
  • Nearby GPU- NN based liveness for selfie use-case executed on GPU
  • Nearby ANY - NN based liveness for selfie use-case executed on any resource (GPU or CPU) according to their current utilization.

NEARBY LIVENESS SCORE THRESHOLDAnything below this value from nearby liveness check will be considered as spoof
Available only for Nearby CPU and Nearby GPU spoof detector resource
900 ↔︎ 100
BODY PARTS DETECTOR RESOURCE

Choose liveness approach for spoof detector.

You can choose from:

  • None - no spoof detection enabled
  • Body parts - spoof detection based on body pose (hands holding printout of static photo or a tablet)

Feedback display
FEEDBACK DISPLAYOpens/Copy the [feedback display] (/docs/how-it-works/smartface-station/sf-station-feedback-display/) link for selected camera
Camera preview
PREVIEW ENABLEDEnable preview generation with embedded graphics. The preview is generated as an MPEG1 stream. You can define the stream quality in the PREVIEW QUALITY setting.Disabled
PREVIEW QUALITY

Define the quality of generated stream.

You can choose from:

  • Low (height: 426 px, bit rate: 153,000)
  • Medium (height: 640 px, bit rate: 450,000)
  • High (height: 1280 px, bit rate: 1,400,000)

Low
PREVIEW PROFILES

Define predefined profile what attributes will be displayed near to the detected or identified object.

Four predefined profiles are available:

  • Minimal (bounding box)
  • AC/Security (bounding box, watchlist member name)
  • Retail (bounding box, watchlist member name, age, gender)
  • Full (bounding box, watchlist member name, age, gender, order, facesize / pedestrian size, confidence / pedestrian quality, template quality, yaw, pitch, roll)

You can create your custom profile with different set of attributes via REST API.

Minimal
ℹ️ Starting from version of SmartFace Platform 5.4.23, the system is capable of linking detected faces to the corresponding body. The facial and pedestrian data are stored in the database only if the "All" save strategy is chosen for both face and pedestrian detection.

Delete camera

The SmartFace Station allows you to delete camera that is processed by the SmartFace Platform. To delete a camera in SmartFace Station, follow these steps:

  1. Click on Cameras in the left menu panel.
  2. Open Camera configuration by clicking on utem in camera list.
  3. Click on DELETE button and click on option OK in confirmation window.

Edge stream management

The SmartFace Station allows you to set up and configure Edge Stream that will be processed by the SmartFace Platform. In the next chapters, you can find information how to:

Set up new edge stream

The SmartFace Station allows you to register an Edge Stream camera in the SmartFace Platform. When registering the camera, you can set its name and configure the video source. To do so, follow these steps:

  1. Click on Configuration in the left menu panel.
  2. Click on ADD EDGE STREAM button on the right side of the dashboard.
  3. Enter the Edge stream name and Client ID.
  4. To create a new edge stream, click on ADD EDGE STREAM button.

⚠️ Please note that you may register only as many edge streams as you have registered edge stream services on SmartFace Platform server.

Enable/Disable edge stream

When you enable an edge stream in the SmartFace Station, SmartFace Platform will start to process the video stream from the edge stream and SmartFace Station will start to display notifications and successful passages. For more information about the edge stream configuration, see edge stream configuration.

To enable or disable a registered edge stream in the SmartFace Station:

  1. Click on Cameras in the left menu panel.
  2. Open Edge stream configuration by clicking on item in camera list.
  3. You may either:
    • Enable the Edge stream, by switching on the toggle button Enabled (appears green).
    • Disable the Edge stream, by switching off the toggle button Enabled (appears red).

Enabled edge stream

Disabled edge stream

Edge stream configuration

The SmartFace Station allows you to configure Edge streams. The Edges tream configuration directly impact the processing of video streams by the SmartFace Platform.

To modify the Edge stream configuration:

  1. Click on Cameras in the left menu panel.
  2. Open Edge stream configuration by clicking on item in camera list.
  3. Now, you can modify Edge stream name and Edge stream configuration parameters.

Edge stream configuration parameters

Parameter nameDescriptionDefault value
General
NAMEThe edge stream name.Provided string.
CLIENT IDA direction to the edge stream.Provided string.
Face detection
FACE SAVE STRATEGY

The strategy for saving data from all detections, you can choose from:

  • All- All faces for the detected person are stored.
  • FirstFace - Only the first detected face of a person is stored.BestFace - Only the best face for the detected person is stored. Which face is the best is decided when the person is lost from tracking.
  • FirstFace, BestFace - The first and the best face for the detected person are stored.
  • MatchedOnly - Only faces which are matched against a watchlist member are stored.

⚠️Set this wisely. Strategy to save all detected objects can generate huge amount of data.

BestFace
Face extraxtion
TEMPLATE GENERATOR RESOURCEChoose between these resources for template extraction:

  • CPU - to perform the template extraction on CPU resource.
  • GPU - to perform the template extraction on GPU resource. GPU must be present in the system.
  • ANY - to perform the template extraction on any resource (GPU or CPU) according to their current utilization. GPU must be present in the system.

CPU
Watchlists synchronisation and matching
SELECTED WATCHLISTSYou can select watchlists which will be synchronised to the edge stream. You can choose from All, None or specific watchlists.All
SYNC TO DEVICEEnables synchronisation of watchlists and watchlist members created in SmartFace to the edge stream.Disabled
Spoof detection
DISTANT DETECTOR RESOURCE

Choose liveness approach for spoof detector.

You can choose from:

  • None - no spoof detection enabled
  • Distant CPU - NN based liveness for access control use-case executed on CPU
  • Distant GPU - NN based liveness for access control use-case executed on GPU
  • Distant ANY - NN based liveness for access control use-case executed on any resource (GPU or CPU) according to their current utilization.

DISTANT LIVENESS SCORE THRESHOLDAnything below this value from distant liveness check will be considered as spoof.
Available only for Distant CPU and Distant GPU spoof detector resource
900 ↔︎ 100
NEARBY DETECTOR RESOURCE

Choose liveness approach for spoof detector.

You can choose from:

  • None - no spoof detection enabled
  • Nearby CPU - NN based liveness for selfie use-case executed on CPU
  • Nearby GPU- NN based liveness for selfie use-case executed on GPU
  • Nearby ANY - NN based liveness for selfie use-case executed on any resource (GPU or CPU) according to their current utilization.

NEARBY LIVENESS SCORE THRESHOLDAnything below this value from nearby liveness check will be considered as spoof
Available only for Nearby CPU and Nearby GPU spoof detector resource
900 ↔︎ 100
Feedback display
FEEDBACK DISPLAYOpens/Copy the [feedback display] (/docs/how-it-works/smartface-station/sf-station-feedback-display/) link for selected camera
ℹ️ Starting from version of SmartFace Platform 5_4.23, the system is capable of linking detected faces to the corresponding body. If at least one of these linked objects (face or body) is saved into the database, the related object (face or body) is also stored in the database, regardless of the set save strategy.

Delete Edge stream

The SmartFace Station allows you to delete edge stream that is processed by SmartFace Platform.

To delete an edge stream in SmartFace Station:

  1. Click on Cameras in the left menu panel.
  2. Open Edge stream configuration by clicking on item in camera list.
  3. Click on DELETE button and click on option OK in confirmation window.

Feedback display

SmartFace Station is designed to provide valuable information to both your security staff and the individuals passing through your access points. This includes notifications about successful passages and unsuccessful access attempts. To enhance the user experience, SmartFace Station allows you to display this information directly to the person accessing the point through a feedback display. This feature can be enabled on a mobile device (tablet) positioned near your access points or on any other device capable of running the Chrome browser.

Example of the feedback display installed next to a speedgate.

Available notifications

The feedback display offers following screens with showing notifications about recognized events:

  • Welcome screen - A person was identified and access was granted.
  • Put on mask screen - A person was identified, but access was not granted due to missing face mask.
  • Access not allowed screen - A person was not identified as a member of any watchlist and passage is not allowed.
  • Access not granted screen: A person was identified as a member of a restricted watchlist or a spoof was detected and passage is not allowed.
  • SmartFace logo screen: The default screen shown after the notification was displayed.
  • Error screen: The error screen is displayed when a problem occurs.

Welcome screen

Put on mask screen

Access not allowed screen

Access not granted screen

SmartFace logo screen

Error screen

Enable feedback display

The feedback display is accessible through the web browser and is available per camera. To access the feedback display open camera details on Configuration screen:

  1. Open SmartFace Station.
  2. Go to Cameras in the left menu.
  3. Click on the desired camera or edge stream.
  4. Click on the button OPEN or COPY LINK to open the feedback display screen in the new tab of your browser or copy the url link for the feedback display screen:

Feedback display prerequisites

The feedback display feature is designed to be used on a mobile device. It is vital to the proper function of the feedback display that the SmartFace Platform and Access Controller is visible from the device where feedback display is running, ie. mentioned modules are accessible from the device. Please take in an account that feedback display URL and a port can be changed when KeyCloak authentication is deployed on your server. For more information about the KeyCloak see Authentication and user management chapter.

We also recommend to use a kiosk mode on your mobile device installed in the field to prevent people in front of your access points to interact with the mobile device.