Versions Compared

Old Version 30

changes.mady.by.user Bahdan Tsiulkou

Saved on

compared with

New Version 31

changes.mady.by.user Bahdan Tsiulkou

Saved on

Key

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

...

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 server
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 uses will use the Intel Quick Sync Video technology. Otherwise, CPU resources 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 is used further.
  3. 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 this case, the source resolution 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 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 don't need to select the standard neural networks in this field, the system automatically selects the required one. If you use a custom neural network, enter a path to the file.

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 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 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, the detector works on the basis of the algorithm without using the neural network on the CPU, ignoring the value specified in the Neural network file field.

  2. If you select the Yes value:

    1. If you don't select the value in the Neural network file field, the system automatically selects the required standard neural network for the device specified in the Neural network mode field.

    2. If you select a custom neural network in 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 is created.

Note
titleAttention!

If you specify the neural network file incorrectly, the detector doesn't work. The neural network algorithm recreates itself every 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!

 

 

 

 

 

 

 

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]

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]

...