Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  1. Select the Facial Recognition object (1). 
  2. If you require using this detection tool for real-time facial recognition, set the corresponding parameter to Yes (2).

  3. If you need to enable recording of metadata, select Yes from the Record Objects tracking list (3).
  4. If a camera supports multistreaming, select the stream for which detection is needed (4). Selecting a low-quality video stream allows reducing the load on the Server.
  5. If you need to save age and gender information for each recognized face, select Yes in the corresponding field (1, see Facial recognition and search). 
  6. In some cases, the detection tool may take other object for a face. To filter out non-facial objects, select Yes in the False Detection Filtering field while calculating the vector model of a face and its recording into the metadata DB (2). If the filtering is on, false results will appear in the detection feed but will be ignored during searches in Archive.
  7. Analyzed framed are scaled down to a specified resolution (3, 1280 pixels on the longer side). This is how it works:

    1. If the longer side of the source image exceeds the value specified in the Frame size change field, it is divided by two.

    2. If the resulting resolution falls below the specified value, it is used further.

    3. If the resulting resolution still exceeds the specified limit, it is divided by two, etc.

      Info
      titleNote

      For example, the source image resolution is 2048 * 1536, and the limit is set to 1000.

      In this case, the source resolution will be divided two times (down to 512 * 384): after the first division, the number of pixels on the longer side exceeds the limit (1024 > 1000).


  8. Specify the minimum and maximum sizes of detectable faces in % of the frame size (4). 
  9. Set the face authenticity threshold required to activate the detector (5). The value is specified empirically in the range of [1, 100]. The higher this value, the fewer faces will be recognized, but the detection quality will be higher.

  10. Set the time (in milliseconds) between face search operations in a video frame in the Face search period field (6). Acceptable values range: [1, 10000]. Increasing this value decreases the Server load, but can result in some faces being missed. 

  11. Enter the time in milliseconds after which the face track is considered to be lost in the Track loss time field (7). Acceptable values range: [1, 10000]. This parameter applies when a face moves in a frame and gets obscured by an obstacle for some time. If this time is less than the set value, the face will be recognized as the same.

  12. Select a rectangular area to be searched for faces in the preview window. To select the area, move the intersection points .

  13. Click the Apply button.

...