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:
You can use the test functionality to quickly see the output produced by the model given your configured input.
You can control both the output frequency (e.g., how often outputs are send to the appplication platform) and the inference speed.
- Output frequency can be set from "as quickly as possible" (basically everytime an image is fed to the AI model), to aggregate once a minute. When selecting an aggregated sending of data the data will be grouped per inference.
- The inference frequency can be set to as fast as possible, or to once every x milliseconds. Note that it is also possible to trigger an inference upon an external signal; this currently is only available through the advanced settings.
A number of models provide their own specific output options. For example models that support an alarm will force the menu below to show in the AI manager:
Here you can set the AI manager to only send output whenever a specific number of objects is detected or whenever an alarm is raised. The sent alarm can be accompanied with the image triggering alarm if desired, also, it's possible to receive a notification by email whenever an alarm is raised.
For model development it is often useful to grab training images within the actual context of use. The AI manager can be used to flexibly grab images whenever a model's output (class membership) is uncertain. This option is contextually available for appropriate models and it is easy to toggle on or off.
Note that by default (re-)training images are captured to the Scailable platform. In the advanced settings you can change the target destination.