Configuring the Fire detection and Smoke detection modules

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

The Fire detection and Smoke detection modules are configured similarly and as follows:

1. Go to the settings panel of the appropriate module.
   

2. In the Minimum alarm time, s field, enter the time period in seconds during which the repeated fire/smoke alarms are ignored.

   Note

   For example, if you set 5 seconds in the Minimum alarm time, s field, and there is a fire/smoke on the image during a longer period of time, then in order to avoid receiving messages about the fire/smoke from the detector every 5 seconds, set a higher value for the Minimum alarm time, s parameter (for example, 10 seconds). In this case, only one message about the fire/smoke is displayed, and all the following alarms aren't displayed in the Event viewer until the time interval between the recognitions of the fire/smoke becomes longer than 10 seconds.

3. Set the Track alarm end checkbox if it is necessary to generate an end-of-alarm event only after the expiration of the time, which is counted as the time of the last received alarm + time specified in the Minimum alarm time, s parameter.
4. Set the Generate alarm on camera checkbox if it is necessary to initiate an alarm on the camera when a detector is triggered.
5. By default, the standard (default) neural network is initialized according to the device selected in the Device drop-down list. The standard neural networks for different types of processors are selected automatically. If a custom neural network is prepared for use, in the Tracking model field, click the button, and select the file in the standard Windows Explorer window that opens.

6. In the Detection sensitivity [0, 100] field, enter the sensitivity of the detector—an integer value in the range from 0 to 100. This parameter determines at what certainty of fire/smoke detection the detector will trigger: the higher the sensitivity, the higher the recognition threshold. For example, at sensitivity 100, the detector neural network must get 100% certainty for some period of time when processing the frames. The value of the Detection sensitivity field is determined experimentally.

7. In the Frames processed per second [0.016, 100] field, set the number of frames per second that will be processed by the neural network. This value affects the processor load: the higher the value, the greater the load. It also affects the operation speed of the algorithm: the higher the frame rate, the faster the required number of frames are collected for making a decision and triggering an alarm, if required.

8. In the Number of frames for analysis and output [5, 20] field, enter the minimum number of frames in the range 5–20 for the detector to analyze before triggering. The higher the value, the more reliable the result of the detector operation. At the same time, if the value is too high, the short-time fire/smoke can be missed. If you enter a value less than the minimum, the value is set to 5.

   Note

   Multiplication of Minimum alarm time, s and Number of frames for analysis and output [5, 20] values is the time period (in seconds) after which the alarm will trigger after the fire/smoke detection.

9. Set the Scanning mode checkbox to track small objects. If you enable this mode, the load on the system increases. So we recommend specifying a small number of frames processed per second in the Frames processed per second [0.016, 100] field. By default, the checkbox is clear. For more information on the scanning mode, see Configuring the Scanning mode.
   

   Note

   You cannot configure the scanning windows for the Fire detection and Smoke detection modules. The default parameters are used.

   When you use scanning mode, we recommend using a full frame without specifying the area of interest in step 11.

10. From the Device drop-down list, select the device on which the neural network will operate: CPU, one of NVIDIA GPUs, or one of Intel GPUs. Auto (default value)—the device is selected automatically: NVIDIA GPU gets the highest priority, followed by Intel GPU, then CPU.
    

    Attention!

    1. We recommend using the GPU.
    2. It can take several minutes to launch the algorithm on NVIDIA GPU after you apply the settings. You can use caching to speed up future launches (see Optimizing the operation of neural analytics on GPU).
11. Specify the area of interest on the video image:
    1. Click the Stop video button to capture the video image.
       
    2. Click the Area of interest button.

    3. On the captured video image, set the anchor points of the area, the situation in which you want to analyze, by sequentially clicking the left mouse button. After you add an area, the rest of the video image is darkened. If you don't specify the area of interest, the entire frame is analyzed.
       

    4. Click the OK button.

       Note

       • To remove the area, click the button next to the Area of interest button.
       • You can add only one area. If you try to add a second area, the first area will be deleted.
12. Click the Apply button.

Configuring the Fire detection and Smoke detection modules is complete.