Use FindFace Multi Functions

FindFace Multi offers a variety of functions to use. Some of them are available out of the box, while others require configuration.

In this section:

Main Menu Functions

FindFace Multi basic functions are available from the web interface. The main menu may display a different number of items depending on whether a functionality is included in your license or not. Also, some functions should be enabled in the configuration file in order to appear in the main menu list.

Here you will find information on whether a function requires configuration or purchase of a license. The majority of functions are described in this documentation. Follow the link to a certain section to read an instruction on how to enable the functionality, if applicable, and how to work with it.

Note

The majority of FindFace Multi functions require resources to operate, namely: cameras, extraction API instances, TNT API objects. These items are licensed separately, and are not covered by this instruction. To find the resources enabled in your license, navigate Licenses → General.

If you prefer working with the console, execute the following command to see the resources, enabled in your license:

curl http://localhost:3185/v1/licenses.json -s | jq

Important

A user must have relevant permissions to work with this or that functionality. Read about user role permissions in the Role and User Management section.

• Record Index: available out of the box, non-configurable, included in the license by default (purchase is not required). There’s no option to disable this functionality.

• Counters: available out of the box, configurable, included in the license by default (purchase is not required). There’s no option to disable this functionality. Refer to this section to configure counters.

• Video Wall: available out of the box, configurable, included in the license by default (purchase is not required). In a Video Wall, the display of object attributes within a bbox depends on the enabled detectors and features. You can enable or disable object and attribute recognition by following these instructions: Enable Face and Face Attribute Recognition, Enable Body and Body Attribute Recognition, Enable Vehicle and Vehicle Attribute Recognition.

• Clusters: disabled by default, configurable, included in the license by default (purchase is not required). FindFace Multi supports automatic clustering of objects of the same origin: face/body/vehicle clustering. Clustering algorithms fall into real-time clustering and scheduled clustering. Read how to Enable and Configure Clustering for an object or apply a certain clustering algorithm. For clustering, it is important that the episodes service is enabled in the findface-multi-legacy.py configuration file.

  sudo vi /opt/findface-multi/configs/findface-multi-legacy/findface-multi-legacy.py
  
  SERVICES = {
      "ffsecurity": {
          "episodes": True,
          ...
      }
  }
  

• Interaction Tracking: disabled by default, configurable, included in the license by default (purchase is not required). To harness this functionality, you must enable face clustering and real-time clustering.

• Alert Manager, Alarm Feed, Alarm Monitor, delivery channels: license purchase is required. This functionality will become available once you have activated the Alerts functional module within your license. To use a Telegram bot as a delivery channel, you should configure it first.

• Maps: license purchase is required. This functionality will become available once you have activated the Maps functional module within your license. Configure the parameters if necessary.

• BI Analytics: installation is required, license purchase is required. This functionality will become available once you have activated the Bi Analytics functional module within your license. The analytical service and the Superset BI system are deployed together with FindFace Multi from one distribution package. Select the appropriate items during installation.

  Q: Do you want to install Analytics service?(y/n)

  A: By answering y you will install the service, which will process FindFace Multi data for further use in analytical purposes. The analytics works for line crossing only at the moment.

  Do you want to install Analytics service?(y/n)
  enable_analytics> y
  

  Q: Do you want to install Superset BI?(y/n)

  A: Installation of the external BI system allows you to view FindFace Multi data (currently available for line crossing only) in the external system in the form of a graph. FindFace Multi serves as a data source, the external BI system helps visualize data. By answering y you choose to install the Apache Superset open-source software application. If you prefer your own BI system, you can skip the suggested installation and answer n.

  Do you want to install Superset BI?(y/n)
  install_superset> y
  

• Line Crossing: license purchase is required. This functionality will become available once you have activated the Line Crossing functional module within your license.

• Search: available out of the box, non-configurable, included in the license by default (purchase is not required).

Other Functions

• External Detectors: available out of the box, non-configurable, included in the license by default (purchase is not required). This functionality cannot be disabled.

• Processing of an uploaded video: available out of the box, included in the license by default (purchase is not required). There must be relevant role permissions enabled for the videoarchive entity for a user who wants to employ this functionality.

• External VMS: disabled by default, configurable, license purchase is required. To use this functionality, you must activate the External VMS functional module within your license and request the VMS integration plugin from an NtechLab representative. Afterward, configure the plugin using this instruction.

• PACS: a standalone service that is used for partner integrations, license purchase is not required. To get an installer and configure the service, please contact an NtechLab representative.

• Liveness: installation is required, configurable, license purchase is required. This functionality will become available once you have activated the Liveness attribute within your license. Face liveness detection can be automatically enabled and configured during the installation.

  Q: Enable liveness and attempt to continue installation?(y/n)

  A: This question appears if you have requested installation and configuration of the object detection and object attribute recognition functions. To install the embedded face liveness detector, enter y. Enter n otherwise.

  Enable liveness and attempt to continue installation?(y/n)
  enable_liveness> y
  

  If you answered n on this step, you can manually enable liveness later, following the instruction in the Enable Face Liveness Detection section.

  After liveness has been installed (or manually configured), you have to enable it in a camera video processing parameters.

  

• Object attributes: installation is required, configurable, license purchase is required. To use an object attribute recognition, you must activate this attribute within your license. Object attributes are licensed within the FindFace Server (the core part of FindFace Multi). Execute the following command to find the full list of attributes available for licensing:

  curl http://localhost:3185/v1/licenses.json -s | jq
  
  "products": {
    ...
    "server": {
      ...
      "features": {
        "body_bags": {
          "value": true
        },
        ...
        ...
      },
  

  Detectors and attributes can be automatically configured during FindFace Multi installation. The installer will ask you several questions (refer to the installation instruction, questions 4.9-4.12). Or you can manually enable recognition of objects and their attributes: Enable Face and Face Attribute Recognition, Enable Body and Body Attribute Recognition, Enable Vehicle and Vehicle Attribute Recognition.

• Video recording: installation is required, configurable, license purchase is required. To use this functionality, you must activate the Video recording functional module within your license. To install the Video Recorder, answer y during installation:

  Do you want to install Video Recorder?(y/n)
  install_video_recorder> y
  

  For configuration, refer to the section Configure Video Recorder. Once a Video Recorder is deployed and configured, you will see the Record video checkbox appear in the main camera settings. Enable video recording in camera settings.

  

• Episodes and Events:

  • Episodes: available out of the box, configurable, included in the license by default (purchase is not required). To disable this functionality, set "episodes": False in the SERVICES section of the findface-multi-legacy.py configuration file.

    sudo vi /opt/findface-multi/configs/findface-multi-legacy/findface-multi-legacy.py
    
    SERVICES = {
        "ffsecurity": {
            "episodes": False,
            ...
        }
    }
    

    It is possible to configure episodes. A user role should have relevant permissions to receive a notification about a new episode.

  • Events: available out of the box, included in the license by default (purchase is not required). Required role permissions (depending on the object): faceevent, bodyevent, carevent.