Documentation for C-Werk 2.0.

Previous page Camera requirements for the Privacy masking detection tool  Pose detection tools Next page

Camera requirements for the Privacy masking detection tool

Hardware requirements for neural analytics operation

To configure the Privacy masking detection tool, do the following:

  1. To record mask to the archive (see Displaying information from a detection tool (mask)), set Yes for the corresponding parameter (1).
  2. Select a processing resource for decoding video streams (2). 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.
  3. Set the detection threshold (3). The value should be selected empirically in the range [5, 100]. The higher the value, the higher the sensitivity to object recognition and masking.

  4. Select the processor for the neural network—CPU, one of NVIDIA GPUs, or one of Intel GPUs (4, see Hardware requirements for neural analytics operation, General information on configuring detection).

    Attention!

    • 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.
    • 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).
    • Starting with Detector Pack 3.11, Intel HDDL and Intel NCS aren’t supported.
  5. If the detection tool cannot correctly identify the object in the frame, you should use the Neural network (5):
    1. If No is selected, the detection tool will operate on the basis of the algorithm without using a neural network, ignoring the value specified in the Neural network file field.
    2. If Yes is selected, and in the Neural network file field a custom neural network is selected that is a privacy masking neural network, a detection tool with a neural network algorithm based on this network will be created.

  6. Select the neural network file (6). 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.

  7. Set the frame rate value for the detection tool to process per second (7). This value should be in the range [0.016; 100].
  8. If you want to exclude complex areas (foliage, water, etc.) from the analysis of the camera FOV, set one or more exclude areas similar to the Object Tracker (see Setting General Zones for Scene analytics detection tools) inside which the detection won’t be performed.

Configuring the Privacy masking detection tool is complete. 

Attention!

Correct operation of the detection tool isn't guaranteed before 10 minutes from the moment of its creation or making any changes in the detection tool settings.

  • No labels