Edge AI development kit for computer vision on a microcontroller

February 18, 2021 //By Nick Flaherty
Edge AI development kit for computer vision on a microcontroller
The FP-AI-VISION1 kit includes ST’s 5Mpixel colour camera module for edge AI applications on the STM32H747 microcontroller

STMicroelectronics has launched an edge AI firmware pack and camera module based around its STM32 microcontrollers (MCUs).

The FP-AI-VISION1 contains several code examples demonstrating complete computer-vision applications running a convolutional neural network (CNN) on the STM32H747 microcontroller and easily portable on all STM32 MCUs. The firmware, part of the STM32Cube eco-system, includes several application examples but lets developers retrain the neural networks with their own 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 create a convenient visual “wakeword” for reactivating a system from power-save mode.

The B-CAMS-OMV camera bundle is optimized for use with FP-AI-VISION1 and provides the hardware required for training and deployment. The bundle contains ST’s MB1379 5-Mpixel OV5640 colour camera module fitted to an adapter card compatible with all STM32 Discovery and Evaluation boards with a ZIF connector. The adapter card can also be used with the ST VG5661 automotive grayscale global-shutter camera. In addition, Waveshare and OpenMV connectors can be used to 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 quantized model generated by X-CUBE-AI, ST’s optimized C-code generator for artificial neural networks. Support for flexible memory configurations allows fine-tuning the model for the intended application.

The function pack can be downloaded free of charge from  www.st.com. The B-CAMS-OMV camera-module bundle is ready to order from  www.st.com and distributors, for $56.00.

www.st.com

Related edge AI articles 

Other articles on eeNews Europe 


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.