Neural Empty Shelf Detector

The Neural Empty Shelf Detector is intended to build up video surveillance systems which require the detailed analysis with the help of the neural networks. As a result, the video surveillance operator will monitor the shop shelves state in real time.

Important

Neural empty shelf detector features:

  • This plugin operates on NeuroStation video recorders or on any video recorder which has TRASSIR 4 installed and is connected to NeuroStation server, which will be used as Analytics server. Read more about server connection in Connecting to a new server.

  • Check the Enable remote analytics flag in the user's settings, which will be connected to the analytics server.

To activate the plugin, go to the Channel settings to the Software detectors area, select the Neural Empty Shelf Detector and then select the Server which will calculate the analytics.

Press Setup empty shelf detector to open the settings window.

Detector

The detector's parameters are set up on the Detector tab.

  • Set the detector's Sensitivity and specify the Detection time in the base settings.

  • You can create the zones in which empty space on the shelves will be swept in the Object sizes settings group. Set the biggest and the smallest sizes of the detected objects with the help of Minimum object size and Maximum object size settings.

Object counting

The Object counting tab lets you create the zones to detect empty spaces on the shelves. There is already a default zone created, which occupies the entire image. You can correct its sizes by changing the position of the angles.

To create a new counting zone press and set its vertices on the images, starting from the upper right and then in the clockwise direction. In order to finish the zone drawing, place the mouse cursor to the zone starting point and then left-click or press CTRL+ENTER.

Tip

Counting zones requirements:

  • The zones should be four cornered.

  • The zones should be drawn in such a way, so they won't capture price tags or shelves partitions.

  • To detect holes in the first or the bottom row only, the zone should be drawn in such a way, so the goods from the second row stay outside this zone.

For each created zone should be setup parameters by which the detector will detect empty spaces on the shelves:

  • Number of products - is the number of the units of goods or the piles of goods, aligned in a row by the counting zone.
  • Hole size is the number of the units of goods or piles, the absence of which will be detected by the detector.