Hardware requirements for neural analytics operation

Camera requirements for the operation of the Fire Detection are given in the table:

Camera
  • We recommend using color cameras. With black and white cameras, the detection quality can be noticeably worse
  • Resolution must be at least 640x360
  • FPS directly affects detection efficiency. In most cases, the default value (1 detection per 10 seconds) is sufficient to detect fires that last more than one minute
Scene
  • The minimum fire area in the frame depends on the neural network that you use. For a standard neural network (see Configuring Fire Detection), the fire area must occupy at least 10% of the frame

    In some cases, when fire is clearly visible, the width/height of the fire area can be sufficient at 1-3% of the frame width/height.

  • Fire must be visually separated from the background

If you set a rectangular recognition area for the detection tool, the limitations apply to this area rather than to the entire frame (see Configuring Fire Detection).