Documentation for Detector Pack 2.8. Documentation for other versions of Detector Pack is available too.

Previous page Configuring detection modules  Data collection requirements for neural network training Next page


Software and hardware requirements

The detector pack uses the AI analytics based on neural networks. The following AI features are available:

  1. Neurotracker (see Neurotracker).
    Neural Tracker detects only objects of a specified class. The Neural Tracker is more accurate than the regular one, and detects even static objects, but it requires more computing resources.

  2. AI Smoke and Fire detection (see Fire detection and Smoke detection).
    Neural network detects fire and smoke in FoV.

  3. AI Person location tracker (see Person location tracker). 
    AI-powered Posture Detection captures specific human poses that may represent a security threat.
  4. Neurocounter (see Neurocounter).
    Neural network counts the number of objects in a given area.
  5. Sweethearting detection (see Sweethearting at checkout detection).
    Neural network detects the theft of goods by cashiers who do not scan barcodes of some items at the checkout.
  6. Equipment detection (see Equipment detection (PPE)).
    Neural network divides the human body into segments, detects the equipment (PPE) on a given body segment, and checks its condition.

The quality of work and the resource consumption of the AI-based detection tools directly depend on the optimization of the neural network model used.

Notes

The file names for each neural network model depend on the device on which the neural network will operate:

  • If you intend to use a CPU or Intel GPU (integrated video core), then it is necessary to train the neural network file using the OpenVINO toolkit, and the name of the neural network file should contain the _openvino substring at the end. For example, test1_openvino.ann.
  • If you intend to use a GPU (NVIDIA graphics processor), then the name of the neural network file should contain only the name of the neural network. For example, test1.ann.
  • If you intend to use the Intel NCS or Intel HDDL, then the name of the neural network file should contain the _movidius substring at the end. For example, test1_movidius.ann.
  • Also, there should be a file with the *.txt extension in the same directory as the neural network file with the *.ann extension. The *.txt file should have the same name as the *.ann file.

Before you start setting up the AI-based detection tools, you should contact the AxxonSoft technical support and request the model files of the trained neural networks. Technical support specialists will request the required data (see Data collection requirements for neural network training) and then provide the files for each neural network model. These files should be distributed to all Servers where you plan to use the detection tools.

Attention!

The startup (initialization) time of each neural network on NVIDIA GPU can take 2-3 minutes, depending on the neural network model that you use. Until initialization is complete, no events will be received from detection tools.

  • No labels