Documentation for Axxon One 1.0.

Previous page General information on metadata  Data collection requirements for neural network training Next page

The Axxon One VMS offers AI analytics based on neural networks. These AI tools include:

  1. Face detection tools (see Face detection tools).
    Neural network detects faces.
  2. Automatic Number Plate Recognition (LPR/ANPR) tools (see Automatic Number Plate Recognition (LPR/ANPR) tools).
    Neural network recognizes vehicle license plates.
  3. Neural Network Filter for Object Tracker (see Setting general parameters of Tracker-based Scene Analytics detection tools).  
    The neural network filter processes the results of the tracker and filters out false alarms on complex video images (foliage, glare, etc.). 
  4. Neural Tracker (see Setting up Neural Tracker-based Scene Analytics detection tools).  
    Neural Tracker detects only objects of a specified class. The Neural Tracker is more accurate than the regular one, and detects even static objects, but it requires more computing resources.
  5. Neural Counter (see Neural Counter).  
    The Neural Counter relies on a neural network to work out the number of objects in the zone.
  6. Smoke and Fire Detection Tools based on Neural Network (see Fire and Smoke Detection Tools).  
    Neural network detects fire and smoke in FOV.

  7. Object detection.
    Neural network is trained on a particular object that will be detected in the frame.

  8. Posture Detection based on Neural Network (see Configure Pose detection tools). 
    Neural network identifies each person's "skeleton" and detects poses that may represent a security threat.
  9. Equipment detection tool based on Neural Network (see Personal protective equipment detection tools).
    Neural network detects the necessary equipment and PPE in the frame. Segmenting and classifying neural networks are used to operate the Equipment detection tool (PPE).

  10. Person-based privacy masking (see Person-based privacy masking).
    Segmenting neural network is used to structure up an image of a human body.

  11. Water Level Detection (see Water Level Detection).
    The detection tool may use the neural network to detect water transparency and level.

Hardware requirements for neural analytics operation

  • No labels

Data collection requirements for neural network training