Output configuration
After selecting a camera and a model, the next step is the selection of the output schedule and location: effectively you can set the "speed" by which the AI model operates, configure how often responses are send out to the application platform, and configure which application platform to use.
By default, the AI manager is set to log its output (i.e., the output form the AI model) to the Scailable platform. Keeping this setting will ensure that data is logged properly (and locally buffered if there is an interrpution in the internet traffic.
Note that only the model output (i.e., the count of the number of people, the license plate, etc.) is logged to the configured application platform. The input images are not stored; they are immediatly discarded after the output is generated. This greatly reduces the amount of data send to the cloud (one of the benefits of edge AI) and greatly improves data security and privacy (some other benefits or edge AI).
The image below show the defailt settings. By default the AI manager will send the output data to the Scailable platform:
However, you can choose any customer REST endpoint you like (that accepts POST requests) to receive the generated output in JSON format:
It is also possible to send the output directly to a SOCKET, where you can senter the path to a local socket.
You can use the test functionality to quickly see the output produced by the model given your configured input.
Last modified 5d ago