The detector pack uses the AI analytics based on neural networks. The following AI features are available:
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.
AI Smoke and Fire detection (see Fire detection and Smoke detection).
A neural network detects fire and smoke in FoV.
- AI Person location tracker (see Person location tracker).
AI-powered Posture Detection captures specific human poses that may represent a security threat. - Neurocounter (see Neurocounter).
A neural network counts the number of objects in a given area.
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.
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 from you the data needed to prepare the models, and then will provide you with the *.ann files for each neural network model. These files should be distributed to all Servers where it is planned to use the detection tools.
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) for the neurotracker operation, 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 the NVIDIA GPU for the neurotracker operation, 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 Neural Compute Stick (Movidius of any generation) or Intel HDDL (a device for working with several Movidius) for the neurotracker operation, 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.
|