This content was written and submitted by the supplier. It has only been modified to comply with this publication’s space and style.
The software architecture allows flexible cloud support.
Through the cloud connection, for example, artificial neural networks are meant to be easily loaded or trained. The AI Vision System Kit is designed to reduce the complexity and need for additional expertise in embedded hardware and software components to provide developers with a more efficient approach to rapid prototyping.
The AI Vision System Kit with Cloud Connection should extend embedded vision development kits with software components that enable flexible access to cloud services. Together with the AI accelerator of the Processing Board, they are meant to form the basis for lean prototyping of AI-based IoT applications for integrated vision systems.
The Kit is made to enable developers to use, train, and deploy machine learning models provided in the cloud on the edge device. For this purpose, pre-trained neural networks are available in the cloud as software containers that are designed for direct use. Users also have the option of expanding these networks as required.
The software containers with the selected machine learning models can be loaded onto the edge device, the embedded system, for prototyping of application examples. The inference and actual image processing should thus be performed on the edge device. In this way, cloud-specific application examples can be tested more easily and with little programming effort, and metadata can be generated. In the next step, users are meant to be able to send the metadata to the cloud via a defined interface and store it in a database, for example, or visualize it with the help of a dashboard using the appropriate tools.
The kit's embedded hardware consists of the Basler dart BCON for MIPI camera with a resolution of 13 MP. The processing board is based on SolidRun's Hummingboard Ripple, an AI optimized board that houses an NXP i.MX 8M Mini SoC and an AI accelerator.
