Versions Compared

Old Version 1

changes.mady.by.user Alina Luchkina

Saved on

compared with

New Version Current

changes.mady.by.user Bahdan Tsiulkou

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Tip

Video stream requirements for the Water level detector

Image requirements for the Water level detector

Hardware requirements for neural analytics operation

To configure the Water level detector, do the following:

  1. Go to the Detectors tab.
  2. Below the required camera, click Create… → Category: Production Safety → Water level detector.

By default, the detector is enabled and set to detect the water level in the frame.

If necessary, you can change the detector parameters. The list of parameters is given in the table:

other will carry the  However will be
ParameterValueDescription
Object features
Record mask to archiveYesBy default, recording of the water level indicator to the archive is enabled. To disable it, select the No value
No
Video streamMain streamIf the camera supports multistreaming, select the stream for which detection is needed. Selecting a low-quality video stream reduces the load on the Serverserver
Other
EnableYesThe detector is enabled by default. To disable the detector, select the No value
No
NameWater level detectorEnter the detector name or leave the default name
Decoder modeAutoSelect 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 are used for decoding
CPU
GPU
HuaweiNPU
Number of frames processed per second10

Specify the number of frames that the detector processes per second. The value must be in the range [0.016, 100]

Note
titleAttention!

The Number of frames processed per second parameter determines the rate of transmitting the frames from the decoder to the detector and affects the water level update rate—the update occurs once per every 23 processed frames. As a result, at low parameter values, there can be a delay between the actual change of the water level value on the image and the generation of the corresponding event.

TypeWater level detectorName of the detector type (non-editable field)
Advanced settings
Frame size change1920

The analyzed frames are scaled down to a specified resolution (1920 pixels on the longer side ) by default). The following algorithm is used:

  1. If the longer side of the source image exceeds the value specified in the Frame size change field, it is divided by two.
  2. If the resulting resolution falls below the specified value, the algorithm stops and this resolution
    3. will be
  3. is used further.
  4. If the resulting resolution still exceeds the specified value, it is divided by two until it is less than the specified resolution.
Info
titleNote

For example, the source image resolution is 2048*1536, and the specified value is set to 1000.  In In this case, the source resolution will be is halved two times (512*384), as after the first division, the number of pixels on the longer side exceeds the specified value (1024 > 1000).  If If detection is performed on a higher resolution stream and detection errors occur, we recommend reducing the compression.

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 You don't need to select the standard neural networks in this field, the system will automatically select selects the required one. If you use a custom neural network, enter a path to the file.

Infonote
Note
titleAttention!
  • You cannot specify the network file in Windows OS. You must place the neural network file locally, that is, on the same server where you install Axxon One.
  • For correct neural network operation on Linux OS, place the corresponding file locally in the /opt/AxxonSoft/DetectorPack/NeuroSDK directory
. 
Note
titleAttention!
  • or in the network folder with the corresponding access rights.
  • If you use a standard neural network (training wasn't performed in operating conditions), we guarantee the overall accuracy of 80-95% and the percentage of false positives of 5-20% (see Data collection requirements for neural network training).
Basic settings
Maximum top value20

Specify the maximum top value of the measuring scale. The value must be in the range [-1000, 1000]

Minimum bottom value0

Specify the minimum bottom value of the measuring scale. The value must be in the range [-1000, 1000]

Neural networkYes

 If If the water in the frame is transparent and the detector cannot correctly identify its level, use Neural network:

  1. If you select the No value
    2. is selected
  2. , the detector
    3. will work based on
  3. works on the basis of the algorithm without using the neural network on the CPU, ignoring the value specified in the Neural network file
    4.  field
  4. field.

    1. If you select the Yes value

    5. is selected

    1. :

      1. If

    6. no value is selected in the

      1. you don't select the value in the Neural network file

    7.  field

      1.  field, the system

    8. will

      1. automatically

    9. select

      1. selects the required standard neural network for the device specified in the Neural network mode field.

      2. If you select a custom neural network

    10. is selected

      1. in

    11. the

      1. the Neural network file field that corresponds to the device specified in the Neural network mode field and is a water-level neural network, a detector with a neural network algorithm based on this neural network

    12. will be

      1. is created.

Note
titleAttention!

If you specify the neural network file is not specified correctlyincorrectly, the detector will not doesn't work. The neural network algorithm will recreate recreates itself every 20 60 seconds.

No
Neural network mode







CPU

Select a processor for the neural network operation (see Hardware requirements for neural analytics operation, Selecting Nvidia GPU when configuring detectors).

Note
titleAttention!
  • another processing resource than the CPU, this device
  • carries most of the computing load.
  •  However, the CPU
  • is also
  • used to run the detector.
  • Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.
  • Starting with Detector Pack 3.14, Intel Multi-GPU and Intel GPU 0-3 are supported.

 

 

 

 

 

 

 

Nvidia GPU 0
Nvidia GPU 1
Nvidia GPU 2
Nvidia GPU 3
Intel GPU
Intel NCS (not supported)
Intel Multi-GPU
Intel GPU 0
Intel GPU 1
Intel GPU 2
Intel GPU 3
Intel HDDL (not supported)
Scale division value1

Specify the scale division value—the difference between the nearest divisions on the scale with numerical markings. The value must be in the range [0.001, 1000]
Image RemovedImage Added

Visible bottom value0Specify the visible bottom value under normal conditions on the measuring scale. The value must be in the range [-1000, 1000]
Visible top value1Specify the visible top value under normal conditions on the measuring scale. The value must be in the range [-1000, 1000]

In the preview window, by moving the anchor points Image Added :

  1. Set the measuring scale in the frame
    2. by moving the anchor points Image Removed.
    Image Removed
  2. .
    Image Added
  3. Specify an upper line, exceeding which the detector generates an event.
  4. Specify the lower line, exceeding which the detector gives a warning, using the orange color of the sensor in the Surveillance window.
Note
titleAttention!
  • When you specify the measuring scale, its top and bottom borders must match the values specified in the Visible bottom value and Visible top value parameters.

...

  • The top and bottom borders mustn't be parallel to the lines of the measuring scale that determines its height. Otherwise, the detector doesn't work properly
Info
titleNote

The water level indicator is displayed in the lower left corner. If the indicator is green, the water level is below high and critical marks. If the indicator is orange, the water level is at high mark, but below critical mark. A red indicator means that water level is above critical mark.

...

  • .
Info
titleNote
  • For convenience of configuration, you can "freeze" the frame. Click the
    • Image Removed
  • Image Added button. To cancel the action, click this button again.
  • To hide the detection area, click the
    • Image Removed
  • Image Added button. To cancel the action, click this button again.
  • The water level indicator appears in the lower left corner. If the indicator is green, the water level is below high and critical marks. If the indicator is orange, the water level exceeds the high mark but is below the critical mark. If the indicator is red, it means that the water level is above the critical mark.

To save the parameters of the detector, click the Apply Image Removed Image Added button. To cancel the changes, click the Cancel Image Removed Image Added button.

Configuration of the Configuring the Water level detector is complete.

When After you have created create the detector, you can see a sensor on the layout in the Surveillance window along with the indicator.

If the sensor icon is green Image Modified, the water level is lower than both critical and high marks. If the icon is orange Image Modified, the water level is above the high mark, but below the critical mark. A red icon Image Modified means that the water level is above the critical mark.

You If necessary, you can also add a numerical value of the water level to the the Surveillance window (see see Configuring display of water level sensor).