You can configure the Sweethearting at checkout detection program module on the settings panel of the Sweethearting at checkout detection object created on the basis of the Camera object on the Hardware tab of the System settings window.

Basic settings of the detector

To configure the Sweethearting at checkout detection program module, do the following:

  1. Go to the settings panel of the Sweethearting at checkout detection object.
  2. By default, the standard (default) neural networks of hand and goods recognition in the frame are initialized according to the device selected at step 3. You must not select manually the standard neural networks for the different processor types since it is performed automatically. If you want to use custom neural networks, click the  button to the right of the Tracking model (Hand recognition in the frame) and Tracking model (Goods recognition in the frame) fields, and in the standard Windows Explorer window that opens, specify the file of the corresponding neural network.
  3. From the Device drop-down list, select the device on which the neural network will operate: CPU, one of the NVIDIA GPUs, or one of the Intel GPUs. Auto (default)—the device is selected automatically: The NVIDIA GPU gets the highest priority, followed by the Intel GPU, then the CPU.
    1. We recommend using the GPU.
    2. It can take several minutes to launch the algorithm on the NVIDIA GPU after you apply the settings. You can use caching to speed up future launches (see Configuring the speedup of neural analytics launch on GPU).

Selecting area of interest

  1. Click the Settings button. The Detection settings window opens.
  2. On the Select area tab, click the Stop video button to pause the playback and capture the frame of the video image.
  3. Click the Area of interest button to specify the area of interest. The button is highlighted in blue color.
  4. On the captured video frame, sequentially set the anchor points of the area using the mouse in which objects are detected, and the remaining part of the frame is darkened. This area must meet the requirements described in the Camera requirements for the Sweethearting at checkout detection module section. If you don't specify the area of interest, the entire frame is analyzed.
    1. You can add only one area. If you try to add the second area, the first area is deleted.
    2. To delete an area, click the button to the right of the Area of interest button.

Configuring the detector parameters

  1. Go to the Parameters tab of the Detection settings window.

     

  2. In the Detection sensitivity [0.0, 1.0] field, specify the detection sensitivity in the range from 0.0 to 1.0. The default value is 0.65.

    The detection sensitivity value is selected experimentally. The lower the sensitivity, the greater the probability of false positives. The higher the sensitivity, the less chance of false alarms, however, some useful tracks can be skipped.

  3. In the Frames processed per second [0.016, 100] field, specify the number of frames per second that the detector processes in the range from 0.016 to 100. The default value is 12.

  4. Click the OK button to save the changes and return to the settings panel of the Sweethearting at checkout detection object.

    To return to the settings panel of the Sweethearting at checkout detection object without saving the changes, click the Cancel button.

  5. Click the Apply button to save the changes.

Configuring the Sweethearting at checkout detection module is complete.