Configuring the Visitors counter detection tool

To configure the Visitors counter detection tool, do the following:

1. Enable the detection tool—select Yes for the corresponding parameter (1).
   
2. Enter the detection tool name or leave the default name (2).
3. If the camera supports multistreaming, select the stream for which detection is needed. Select a low-quality video stream to reduce the Server load (3).

4. Click the button and specify the size of a human (4). You can do this by dragging the anchor points of the rectangular area. You can also specify the size of a human manually by entering into the Human size field (9) the area of the rectangle around a human as a percentage of the frame area. Consider that to calculate the size, the size of the compressed frame is taken into account (7) and not the original size of the video stream. The value should be in the range [1; 75].
   

   Attention!

   When specifying the size of a human, consider the Requirements for the person size in the frame.

   

5. In the preview window, set the detection area (5). The detection area is divided into two sectors—area 1 and area 2. The transition from area 1 to area 2 is the visitor's passage in the "Exit" direction. The transition from area 2 to area 1 is the visitor's passage in the "Entrance" direction.
   If the People indoor counter parameter (11) is enabled:
   1. Transition from area 1 to area 2—minus one to the visitors counter.
      
   2. Transition from area 2 to area 1—plus one to the visitors counter.
      You can configure the sectors, using the anchor points or lines. To swap sectors, click inside one of them. To display/hide sectors in the preview window, click the button.
      
      
6. Select a processing resource for decoding video streams (6). 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.

7. By default, during analysis the frame is compressed to the specified size (7, the default size is 640 pixels on the larger side). The value should be in the range [640; 10000]. The following algorithm is used:

   1. If the original resolution on the larger side of the frame is greater than the one specified in the Frame size change field, then it is divided in half.
   2. If the resulting resolution is less than the specified one, then the algorithm stops and this resolution is used.

   3. If the resulting resolution is still greater than the specified one, then it is divided in half until it becomes less.

      Note

      For example, the original video image resolution is 2048*1536, the specified value is 1000. In this case, the original resolution will be halved 2 times (512*384), because after the first division, the value on the larger side of the frame will be greater than the specified value (1024 > 1000). If detection is performed on a higher resolution stream and detection errors occur, it is recommended to reduce the compression.

      

8. Set the number of frames for the detection tool to process per second (8). This value should be in the range [0.016; 100].

9. By default, the detection tool generates the Camera. Visitor access in the direction of "Entrance" and Camera. Visitor access in the direction of "Exit" events. If you also want to count visitors at the facility, and it is necessary to trigger an alarm when the threshold value is exceeded, do the following:

   1. Select Yes for the People indoor counter parameter (11).

   2. Enter the number of visitors in the area at the time of the detection tool configuration (10). The value should be in the range [0; 100000].
   3. Set the threshold value for the number of visitors, above which the event will be generated (12). The value should be in the range [0; 100000].
10. Click the Apply button.

Configuration of the Visitors counter detection tool is now complete.