Go to documentation repository
Page History
| Tip |
|---|
Camera Video stream and scene requirements for the Fire Detectiondetector Hardware requirements for neural analytics operation Optimizing the operation of neural analytics on GPU in Windows OS |
To configure smoke (fire) detection tool:
...
Optimizing the operation of neural analytics on GPU in Linux OS |
To configure the Fire detector, do the following:
- Go to the Detection Tools tab.
- Below the required camera, click Create… → Category: Production Safety → Fire detector.
By default, the detector is enabled and set to detect fire.
If necessary, you can change the detector parameters. The list of parameters is given in the table:
| Parameter | Value | Description |
|---|---|---|
| Object features | ||
| Record mask to archive | Yes | By default, the sensitivity scale of the |
...
| detector is recorded to the archive (see Displaying information from a |
...
| detector (mask)). To disable the parameter, select |
...
| the No value | ||
| No | ||
| Video stream | Main stream | If the camera supports multistreaming, select the stream for which detection is needed |
...
| . Selecting a low |
...
| quality video stream |
...
| reduces the load on the Server | ||
| Other | ||
| Enable | Yes | The detector is enabled by default. To disable the detector, select the No value |
| No | ||
| Name | Fire detector | Enter the detector name or leave the default name |
| Decoder mode | Auto | Select a processing resource for decoding video streams |
...
| . When you select a GPU, a stand-alone graphics card takes priority (when decoding with NVIDIA NVDEC chips). If there is no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding | |
| CPU | |
| GPU | |
| HuaweiNPU | |
| Number of frames processed per second | 0.1 |
...
| Specify the number of frames that the detector will process per second |
...
| . The value |
...
| must be in |
...
| the range [0 |
...
| .016; 100] |
...
...
| Type |
...
| title | Note |
|---|
...
The default values (five frames for output and 0,1 FPS) indicate that the tool will analyze frame over 50 seconds span. The detection tool analyzes one frame every 10 seconds. If it detects smoke/fire on five consecutive fames, the detection tool will trigger an alert.
...
| Note | ||
|---|---|---|
| ||
|
...
| Fire detector | Name of the detector type (non-editable field) | ||||||
| Advanced settings | |||||||
| Neural network file | Select a neural network file. The standard neural networks for different processor types are located in the C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK directory. You don't need to select the standard neural networks in this field, the system will automatically select the required one. If you use a custom neural network, enter a path to the file.
| ||||||
...
| ||||||
| Ignore black and white image | Yes | The parameter is disabled by default. If you don't want the detector to generate an event when the image is black and white, select the Yes value | ||||
| No | ||||||
| Number of measurements in a row to trigger detection | 5 | Specify the minimum number of frames with |
...
fire |
...
for |
...
the detector to generate an event. The value |
...
must be in the range [5; 20] |
...
| Scanning mode | Yes | The parameter is disabled by default. You can use the scanning mode (see Configuring the scanning mode) to detect small objects or objects in areas far away from the camera |
...
| . For this, select the Yes value. This mode doesn’t provide absolute detection accuracy, but can improve detection performance | ||
| No | ||
| Basic settings | ||
| Mode | CPU | Select a processor for the neural network operation (seeHardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring detectors). |
...
| |||||
| Nvidia GPU 0 | |||||
| Nvidia GPU 1 | |||||
| Nvidia GPU 2 | |||||
| Nvidia GPU 3 | |||||
| Intel GPU | |||||
| Huawei NPU | |||||
| Sensitivity | 33 | Specify the sensitivity of the detector empirically. The value must be in the range [1; 99]. The default value is 33 |
...
. The preview window displays the sensitivity scale of the |
...
detector that relates to the sensitivity parameter. If the scale is green, |
...
fire isn't detected. If the scale is yellow, |
...
fire |
...
is detected, but not enough to |
...
generate an event. If the scale is red, |
...
fire |
...
is detected, and the |
...
detector generates an event, if the scale is red through the sampling period (50 seconds by default |
...
).
|
...
means that the |
...
detector will generate an event when the scale has at least |
...
four divisions full over the entire detection |
...
period. An event will end when the scale has less than |
...
two divisions full over the detection |
...
period. The |
...
detector will |
...
generate an event again if the scale has at least |
...
four divisions full over the entire detection |
...
period |
By default, the entire frame is the detection
...
area. In the preview window, you can
...
specify the detection areas using the anchor points
...
(see Configuring a detection area):
- Right-click anywhere in the preview window.
- Select If you want to specify the detection area by one or more rectangles, select Detection area (rectangle) to set one or several rectangular areas. If you specify a rectangular area, the detection tool detector will work only within its limitsanalyze only this area. The rest of the FOV frame will be ignored.
Select
- If you want to specify the detection area by one or more polygons, select Detection area (polygon) to set one or several polygonal areas. If you specify one or several polygonal areas, the detection tool detector will process analyze the entire FOV while the remaining frame. The part of the FOV frame not included in the specified polygons will be blacked out.
can configure detection areas similarly to privacy masks in Scene analytics detection tools (see Setting General Zones for Scene analytics detection tools).You can use trial and error method to decide which type of detection area (rectangular or polygonal) is more effective in your case. Some neural networks give better detection with rectangles while others are better with polygonsNote title Attention! You
must select the detection area (polygon or rectangle) experimentally. For some neural networks the quality of detection will be better with rectangle, for others—with polygon.
| Info | ||
|---|---|---|
| ||
|
To save the parameters of the detector, click the Apply 
button. To cancel the changes, click the Cancel 
button.
Overview
Content Tools