New STM32Cube Function Pack and Camera-Module for Affordable Edge AI Development

STM32Cube Function Pack and Camera-Module

STMicroelectronics has introduced a new AI firmware function pack and camera-module hardware bundle for allowing embedded developers to build affordable and powerful computer vision applications. The FP-AI-VISION1 comes with several code examples demonstrating complete computer-vision applications running a convolutional neural network (CNN) on STM32H747 and easily portable on all STM32 MCUs.


Optimized for use with FP-AI-VISION1, the B-CAMS-OMV camera bundle contains ST’s MB1379 5-Mpixel OV5640 color camera module fitted to an adapter card compatible with all STM32 Discovery and Evaluation boards with a ZIF connector. The Waveshare and OpenMV connectors allow users to attach various third-party infrared and visible spectrum cameras, which helps in addressing a wider range of computer-vision applications.


The USB VC camera of the device allows simple image acquisition, and code examples for food classification and human-presence detection, this helps in creating a convenient visual wake-word for reactivating from the power-save mode. The FP-AI-VISION1 comes with various frame-buffer processing functions, camera drivers, and software for image capture, pre-processing, and neural-network inference. The function pack can be downloaded free of charge from The B-CAMS-OMV camera-module bundle is ready to order from and distributors, for $56.00.


Feature of FP-AI-VISION1

  • Complete firmware to develop a computer vision application on STM32 microcontroller
  • Image pre-processing library (STM32_Image)
  • Neural Network library optimized for STM32 (STM32_AI_Runtime) generated by using the X-CUBE-AI Expansion Package for STM32CubeMX
  • USB webcam application enabling the STM32H747I-DISCO board to act as a USB video camera (UVC) device when connected to a host
  •  Integration examples based on float and quantized models
  • Libraries enabling the test, debug and validation of the embedded application
  • Support for camera frame capture to enable image dataset collection
  • Sample implementations available for the STM32H747I-DISCO Discovery board connected to the B-CAMS-OMV camera module bundle


Features of B-CAMS-OMV

  • 1 × 30 pin ZIF connector and extended GPIO connector for easy connection to compatible STM32 boards
  • STMicroelectronics camera module (MB1379) connector
  • OpenMV camera module connector
  • Waveshare camera board connector
  • 3.3 V power
  • Based on the OV5640 image sensor offering a 5-Mpixel resolution with 8-bit color
Component Datasheet