Edge AI Development With Computer-Vision Launchpad For STM32 MCUs

This post was originally published on this site
Advertisement

Features include support for USB VC camera (webcam mode), which allows simple image acquisition and code demonstrations

Enabling embedded developers to build affordable and powerful computer-vision applications that run at the Edge is a new AI firmware function pack and camera-module hardware.

The STM32Cube powered function pack, the FP-AI-VISION1 demonstrates computer-vision applications running a convolutional neural network (CNN) on STM32H747 and easily portable on all STM32 MCUs. The firmware proposes several application examples but lets developers retrain the neural networks with their own choice of data sets, giving freedom and flexibility to address a wide variety of use cases.

New features include support for USB VC camera (webcam mode), which allows simple image acquisition, and code examples for food classification and human-presence detection to reactivate a system from power-save mode.

The B-CAMS-OMV camera bundle is optimised for use with FP-AI-VISION1 and provides the hardware required for training and deployment. The bundle contains an MB1379 5-Mpixel OV5640 colour camera module fitted to an adaptor card compatible with all STM32 Discovery and Evaluation boards with a ZIF connector. The adaptor card can also be used with the VG5661 automotive grayscale global-shutter camera.

Also, Waveshare and OpenMV connectors let users attach various third-party infrared and visible-spectrum cameras to address a wider range of computer-vision applications.

Included in FP-AI-VISION1 are various frame-buffer processing functions, camera drivers and software for image capture, pre-processing and neural-network inference. Several neural-network models are available, including a floating-point based model and a quantised model generated by X-CUBE-AI. Support for flexible memory configurations allows fine-tuning the model for the intended application.

The function pack can be downloaded free of charge from the website of STMicroelectronics. The B-CAMS-OMV camera-module bundle is ready to order from STMicroelectronics and distributors.