Documentation for DetectorPack PSIM 1.0.1.

Previous page Camera requirements for the Train detection module  Traffic light detection Next page

Note

It is not recommended to create more than four Train detection objects for the correct operation of the Train detection module.

The Train detection module can be configured on the settings panel of the Train detection object created on the basis of the Camera object on the Hardware tab of the System settings dialog window.

The Train detection module is configured as follows:

  1. Go to the Train detection settings panel.
  2. Click the Settings button. The Detection settings windows will open.
  3. Specify the surveillance area on the video image:
    1. Click the Stop video button to capture the video image (1).
    2. Click the Area of interest button (2).
    3. On the captured video image (3), sequentially specify nodal points of area to be analyzed by clicking the left mouse button (4). It is possible to add only one area. Wheen attempting to add the second area, the first one will be deleted. After area specifying, the remaining part of video image will be darkened.

      Note

      To remove the area, click the button next to the Area of interest button.

      Note

      The surveillance area should be specified in such a way that except for the train movement, there is no other movement.

      Attention!

      Setting the Area of interest is a mandatory requirement for the detection module operation.

  4. Go to the Parameters tab (5) and do the following:
     
    1. In the Frames processed per second [0.016,100] field (6), set the number of frames per second that will be processed by the detection tool.
    2. Click the OK button to save the changes and return to the settings panel of the Train detection (7).

      Note

      To return to the settings panel of the Train detection without saving the changes, click the Cancel button.

  5. Click the Apply button on the Train detection settings panel.

Configuring the Train detection module is complete.

  • No labels