Page History

...

1. Go to the appropriate detector object 's control settings panel.
   

2. In the Minimum alarm time, secs field (1), enter the time period in seconds during which the repeated recognitions of the ignitionfire/smoke alarms will be ignored.

   Info
   title Note
   For example, if 5 seconds is set for the Time in seconds between processed frames parameterin 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 of ignitionabout the fire/smoke from the detector detection tool every 5 seconds, set a set a higher value for the the Minimum alarm time, sec parameter s parameter (for example, 10 seconds). In this case, only one message about the ignitionfire/smoke will be displayed, and all the repeated recognitions all the following alarms will not be displayed in the Event viewer until until the time interval between the recognitions the recognitions of the ignitionfire/smoke 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 considered counted as: " time of the last received alarm " + " time specified in the Minimum alarm time, sec s parameter".
4. Set the Generate alarm on camera checkbox (3), if it is necessary to initiate an alarm on the camera when a detection tool is triggered.

5. If you use a custom unique neural network is prepared for use, in the Tracking model field, click the the button (4), and select the file and in the standard Windows box Explorer window that opens, select the neural network file with the fire/smoke detection model. It is not necessary to select standard neural networks in this field, the system will automatically select the required one. Standard neural networks for different processor types used are located in the . 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)\Intellect\Modules64 directory:

   Neural network name	Detection/CPU
   smoke_openvino.ann	Smoke detection/CPU
   smoke_original.ann	Smoke detection/GPU
   fire_openvino.ann	Fire detection/CPU
   fire_original.ann	Fire detection/GPU

   
   

6. In the Detection sensitivity : [0..100] field (5), enter the sensitivity of detection – the detection tool – integer value in the range from 0 to 100. This parameter has an impact on sufficient probability determines at what certainty of fire/smoke recognition for alarmdetection the detection tool will trigger.

   Info
   title Note
   For example, if the sensitivity is 0, than then the frame on which fire/smoke is recognized with certainty detected with the certainty of more than 95% will be alarmingconsidered alarmed. If the sensitivity is 100, than then the frame with 50% certainty 50% certainty of fire/smoke recognition detection will be alarmingalarmed.

   
   

7. In the Frames processed per second second [0,.016, 100] field (6), set the number of frames per second that will be processed by the detection toolneural network. This parameter value has an impact on processor capacityload: the greater higher the parameter value, the more capacity. Also it greater the load. It also has an impact on the algorithm operation speed of algorithm: the greater higher the frame rate, the faster the required number of frames will be collected for making a decision and triggering an alarm, if it's required.

8. In the Number of frames for analysis and output field (7), enter the minimum number of frames for the detection analysis before alarm generatingtool to analyze before triggering. The more higher the value, the more certain reliable the result of the detection tool operation. At the same time, if the value is too largehigh, the short-time fire/smoke can be missed.

   Info
   title Note.
   Multiplication of Time in seconds between processed frames * of Minimum alarm time, s and Number of frames for analysis and output parameter values characterizes is the time period (in seconds) at the end of which after after which the alarm will trigger after the fire/smoke alarm will be triggereddetection.

   
   

9. In the Device drop-down list (8), select the device on which the neural network will operate. Auto − the device is selected automatically: GPU gets the highest priority, followed by Intel GPU, then CPU.
10. Click the Settings button (9). The Detection settings windows will open.
11. Specify the surveillance area of interest on the video image:
    1. Click the Stop video button to capture the video image (1).
       
    2. Click the Area of interest button (2).

    3. On the captured video image (3) sequentially specify nodal set the anchor points of the area to be analyzed by , the situation in which you want to analyze, by sequentially clicking the left mouse button. It is possible to add only Only one area . While attempting can be added. If you try to add the a second area, the first one area will be deleted. After adding an area specifying , the remaining part rest of the video image will be darkened.
       

    4. Click the OK button (2).

       Info
       title Note
       Specifying the Area of interest is a mandatory requirement for the detection module operation. To remove the area, click the button next to the Area of interest button.
       Note
       title Attention!
       Setting the Area of interest is a mandatory requirement for the detection module operation.

       
       

12. Click the Apply button (10).

...