Page History

The 
• You can configure the Fire detection
 module can be configured
• module on the settings panel of
the 
• the Fire detection object created on the basis of the Camera object on the Hardware tab of the
 System
• System settings
 dialog
• window.
The 
• You can configure the Smoke detection
 module can be configured
• module on the settings panel of
the 
• the Smoke detection object created on the basis of the Camera object on the Hardware tab of the
 System
• System settings
 dialog
• window.
  Image Modified

The To configure the Fire detection and Smoke detection modules are configured similarly and as follows modules, do the following:

1. Go to the settings panel of the
appropriate
2. corresponding module.
   Image Modified
In the Minimum alarm time, s
3. To receive events about the end of fire/smoke only after the time period from the Alarm duration, sec setting, set the Track alarm end checkbox. By default, the checkbox is cleared, which means that events about the end of fire/smoke are received immediately.
4. In the Alarm duration, sec field, enter the time period in seconds during which the repeated fire/smoke
alarms will be ignored

Image Removed

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: time of the last received alarm + time specified in the Minimum alarm time, s parameter
5. alarm events are ignored. By default, the setting isn't available for editing. To enable it, you must set the Track alarm end checkbox (see the previous step).

   Info
   title Note

For example, if 5 seconds is set in the Minimum alarm time, sfield, 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 detection tool 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 will be displayed, and all the following alarms will not be displayed in the Event viewer until the time interval between the recognitions of the fire/smoke becomes longer than 10 seconds.

6. If you set the Track alarm end checkbox, the events about the end of fire/smoke are received after the time specified in the Alarm duration, sec setting. If, until the end of this period, the current fire/smoke is completed and the new one is detected, the detector doesn't generate events about completing the current and starting the new alarm. The new fire/smoke event is received after the current alarm is completed.

7. Set the Generate alarm on camera checkbox
,
8. if
it is necessary
9. you want to initiate an alarm on the camera when
a detection tool is triggered.
10. the detector generates an event.
11. By default, the standard (default) neural network is initialized according to the device selected in step 10. You must not select the standard neural networks for the different processor types manually, since it is performed automatically. If there is
If
12. a unique neural network
is prepared
13. for use,
in the
14. click the Image Added button to the right of the Tracking model field,
click the Image Removed button,
15. and 
select the
16. specify its file in the standard Windows Explorer window that opens
. If the field is left blank, the default neural networks will be used for detection (see the table below). They are selected automatically depending on the CPU and are located in the C:\Program Files (x86)\Axxon PSIM\Modules64 directory:Neural network nameDetection/CPUsmoke_openvino
17. .
ann
18. Smoke detection/CPUsmoke_original.annSmoke detection/GPUfire_openvino.annFire detection/CPUfire_original.annFire detection/GPU

    Image Removed

19. In the Detection sensitivity [0

..

20. , 100] field, enter the detector sensitivity

of the detection tool—

21. —an integer value in the range from 0 to 100. This parameter determines at what certainty of fire/smoke detection the

detection tool will trigger:

22. detector generates an alarm: the higher the sensitivity, the higher the recognition threshold. For example, at sensitivity 100, the

detection tool

23. detector neural network must get 100% certainty for some period of time

when

24. during the frame processing

the frames

25. . The value of the Detection sensitivity field is determined experimentally.

26. In the Frames processed per second [0.016, 100] field, set the number of frames per second that
will be processed by
27. the neural network processes. This value
has an impact on
28. affects the processor load: the higher the value, the greater the load. It also
has an impact on
29. affects the
algorithm
30. operation speed of the algorithm: the higher the frame rate, the faster the required number of frames
will be
31. are collected for making a decision and
triggering
32. generating an alarm, if required.

33. In the Number of frames for analysis and output [5, 20] field, enter the minimum number of frames in the range from 5

-20

34. to 20 for the

detection tool

35. detector to analyze before

triggering

36. generating an alarm. The higher the value, the more reliable the result of the

detection tool

37. 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

. Info

title	Note

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

38. .

39. Set

the

40. the Scanning mode checkbox to track small objects. If you enable this mode, the load on the system

will increase. So

41. increases. That is why we recommend

specifying a

42. setting the small number of frames processed per second

at

43. in step 7. By default, the checkbox is

clear

44. cleared. For more information on the scanning mode, see Configuring the Scanning mode.
    

    Info
    title Note
    You cannot configure the scanning windows for the Fire detection and Smoke detection modules. The default parameters are used. When you use the scanning mode, we recommend using a full frame without specifying the area of interest in step 11.

the
45. From the Device drop-down list, select the device on which the neural network will operate: the CPU, one of the NVIDIA GPUs, or one of the Intel GPUs. Auto
—
46.  (default value)—the device is selected automatically: The NVIDIA GPU gets the highest priority, followed by the Intel GPU, then the CPU.
47. 
    

    Note
    title Attention!
    We recommend using the GPU. It can take several minutes to launch the algorithm on the 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)

Click the Settings Image Removed button. The Detection settings windows will open

48. .

49. Specify the area of interest on the video image:
    1. Click the Stop video button to capture the frame of the video image.
       Image Modified
    2. Click the Area of interest button.

    3. On the captured video

image

50. 1. frame, sequentially set the anchor points of the area using the left mouse button, the situation

in

51. 1. of which you want to analyze

, by sequentially clicking the left mouse button. Only one area can be added. If you try to add a second area, the first area will be deleted. After adding an area, the rest

52. 1. . After you add the area, the remaining part of the video image

will be darkened

53. 1. is darkened. If you don't specify the area of interest, the entire frame is analyzed.
       Image Modified

    2. Click the OK button.

       Info
       title Note

Specifying the Area of interest is a mandatory requirement for the detection module operation.

54. 1. To remove the area, click the Image Modified button next to the Area of interest button. You can add only one area. If you try to add the second area, the first area is deleted.

55. Click the Apply
Image Removed button
56.  button.

Configuring the Fire detection and Smoke detection modules is complete. 

...