Page History

...

1. To record water level detection readings to the archive, set Yes for the Record mask to archive parameter (1).
   

2. If the camera supports multistreaming, select the stream for which detection is needed. Select a low-quality video stream to reduce the Server load (2).
3. Select a processing resource for decoding video streams (3). 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 or the CPU.

4. Analyzed framed are scaled down to a specified resolution (4, 1920 pixels on the longer side). This is how it works:

   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, it is used further.

   3. If the resulting resolution still exceeds the specified limit, it is divided by two, etc.

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

      
      

5. Set the frame rate value for the detection tool to process per second (5). The value should be in the range [0.016; 100].

6. If the water in the frame is transparent and the detection tool cannot correctly identify its level, use Neural network (6):

   1. If No is selected, the detection tool will work based on the algorithm without using the neural network on the CPU, ignoring the value specified in the Neural network file field.

   2. If Yes is selected:

      1. If no value is selected in the Neural network file field, the system will automatically select the required standard neural network for the device specified in the Neural network mode field.

      2. If a custom neural network is selected 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 detection tool with a neural network algorithm based on this network will be created.
         

         Note
         title Attention!
         If the neural network file is not specified correctly, the detection tool will not work. The neural network algorithm will recreate itself every 20 seconds.

         
         

7. Select the neural network file (7). The standard neural networks for different processor types are located in the C:\Program Files\Common Files\Grundig\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.
   

   Info
   title Note
   For correct neural network operation on Linux, place the corresponding file in the /opt/Grundig/DetectorPack/NeuroSDK directory.

8. Select the processor for the neural network—CPU, one of GPUs, or one of Intel processors (8) (see Hardware requirements for neural analytics operation, General information on configuring detection). 
   

   Note
   title Attention!
   It may take several minutes to launch the algorithm on 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). If you specify other processing resource than the CPU, this device will carry the most of computing load. However, the CPU will also be used to run the detection tool. Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.

   
   

9. On the measurement scale (9, 10), set the top and bottom visible values in normal conditions. The value should be in the range [0; 19].
10. Move the anchor points in the preview window:

    1. Set the measurement scale in the frame.
       

       Note
       title Attention!
       Top and bottom values of the measurement scale should match the actual settings (see step 9).

       
       

       Info
       title Note
       Water level sensor is shown in the lower left corner. If the sensor is green, the water level is below high and critical marks. If the sensor is orange, the water level is at high mark, but below critical mark. A red sensor means that water level is above critical mark.

       
       

    2. Draw a line to set the top limit for water level upon reaching which the detection tool triggers an alarm.
    3. Draw a line to set the top limit for water level upon reaching which the detection tool highlights the sensor icon in the video surveillance window with orange color.
11. Click the Apply button.

...