All basic detection tools have a number of common settings.

1. If a camera supports multi-streaming, select the stream for which detection is needed (1). Selecting a low-quality video stream allows reducing the load on the Server.
   

2. The default setting for all detection tools is Decode only key frames (2). In this case, only key frames are decoded. To disable the decoding of key frames, select No in the corresponding field.
   

   This feature reduces the Server load but, as can be expected, negatively impacts the quality of detection. This setting should be activated on "blind" Servers (Servers that do not display video) on which it is necessary to perform detection. For the MJPEG codec, each frame is considered a key frame.

   
   

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's no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding.

4. Event duration to trigger detection (sec.) is the maximum time of the event duration after which the detection tool will trigger (4). But, the detection tool can trigger even earlier if the algorithm undoubtedly determines the noise. If the detection tool does not trigger after the event duration time expires, it means that the corresponding image defect was not detected with the specified detector sensitivity (6).
5. Set the frame rate value for each detection tool to process (5). This value should be in the range [0.016, 100]. 
6. Sensitivity of detection tool operation in standard units from 0 to 100 (6).

To save settings, click the Apply button.