Documentation for Detector Pack 2.7. Documentation for other versions of Detector Pack is available too.

Previous page Configuring the «Smoke detection» module  Configuring the «Fluid level detection» module Next page


Camera requirements for the Fire detection module

Important!

Unlike the standard fire detection systems, the fire detector faces many problems regarding the scene and the background of the video image. Thus, it is not guaranteed that a fire will be detected in all the circumstances. The fire detector should be considered as a system that increases the fire detection possibilities. Thereby, there can still be false alarms and situations when the detector does not react to real cases of fire in the video camera FOV.

At the same time, the fire detector is based on a neural network, which main principle is learnability.

If the fire detector does not react to real cases of fire in the video camera FOV, we suggest you record the video and send it to AxxonSoft. We will train the neural network based on the provided video, the detector pack will be updated, and future detectors operation under the similar conditions will be optimal.

The Fire detection module can be configured on the settings panel of the Fire detection object created on the basis of the Camera object on the Hardware tab of the System settings dialog window.

The Fire detection module is configured as follows:

  1. Go to the Fire detection object's control panel.

  2. In the Minimum alarm time, sec field (1) enter the time period in seconds during which the repeated fire alarms will be ignored.

    Note

    For example, if 5 seconds is set for the Time in seconds between processed frames parameter, and there is a fire on the image during a longer period of time, then in order to avoid receiving messages of ignition from the detector every 5 seconds, set a higher value for the Minimum alarm time, sec parameter (for example, 10 seconds). In this case, only one message about the ignition will be displayed, and all the repeated recognitions will not be displayed in the Event viewer until the time interval between the recognitions of the ignition becomes longer than 10 seconds.

  3. Set the Track alarm end checkbox (2) if it is necessary to generate an end-of-alarm event only after the expiration of the time, which is calculated as: "time of the last received alarm" + "time specified in the Minimum alarm time, sec parameter".
  4. Click the  button (3) and in the standard Windows box that opens select the neural network file with the fire detection model.

  5. In the Detection sensitivity: 0..100 field (4) enter the sensitivity of detection – integer value from 0 to 100. This parameter has an impact on sufficient probability of fire recognition for alarm.

    Note

    For example, if sensitivity is 0, than frame on which fire is recognized with certainty more than 95% will be alarming. If sensitivity is 100, than frame with 50% certainty of fire recognition will be alarming.

  6. In the Time in seconds between processed frames field (5) enter the time period in seconds separating frames used by algorithm for fire analysis. This parameter has an impact on processor capacity: the less the parameter, the more capacity. Also it has an impact on operation speed of algorithm: the less distance between frames. the faster required number of frames will be collected for decision and alarm, if it's required.

  7. In the Number of frames for analysis and output field (6) enter minimum number of frames for detection analysis before alarm generating. The more the value, the more certain the result of detection operation. At the same time, if value is too large, the short-time fire can be missed.

    Note.

    Multiplication of Time in seconds between processed frames * Number of frames for analysis and output parameters characterizes time period (in seconds) at the end of which after fire alarm will be triggered.

  8. In the Device drop-down list (7), select the device on which the fire detection will operate:
    1. Auto - automatic device selection.
    2. CPU - Central Processing Unit from Intel (not recommended).
    3. NVIDIA GPU (depends on the number of NVIDIA  graphics cards installed).
  9. Specify the detection surveillance area on the video image:
    1. Click the Setup button (8). The Detection settings window will open.
    2. Click the Stop video button to capture the video image (1).
    3. Click the Area of interest button (2).
    4. Specify area on which smoke recognition will be detected (3).
    5. Click the OK button (4).
  10. Click the Apply button (9).

Configuring the Fire detection module is complete.