Futurlec - The Electronic Components and Semiconductor Superstore
View Cart

ST Releases New AI Software for Computer Vision

The AI STM32Cube Function Pack enables embedded developers to build computer-vision applications

STMicroelectronics has released a new AI firmware function pack and camera-module hardware bundle enabling embedded developers to build affordable and powerful computer-vision applications running locally, at the Edge, on STM32* microcontrollers (MCUs).

Click for Larger Image - ST Releases New AI Software for Computer Vision The STM32Cube function pack - 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 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 create a convenient visual “wakeword” for reactivating a system from power-save mode. An article is available in the STM32 wiki that shows how to use the Teachable Machine online tool with STM32Cube.AI and the FP-AI-VISION1 function pack to create an image classification application.

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 color 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 let users attach various third-party infrared and visible-spectrum cameras to address a wider range of computer-vision applications An STM32 wiki article is available that shows how to integrate code generated using STM32Cube.AI in the OpenMV ecosystem.

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.

Features of the FP-AI-VISION1 STM32Cube function pack include:

  • Complete firmware to develop a computer vision application on STM32 microcontroller
  • Image pre-processing library
  • Neural Network library optimized for STM32 generated by means of the X-CUBE-AI Expansion Package for STM32CubeMX
  • Food recognition application based on Convolutional Neural Network
  • Person presence detection application based on Convolutional Neural Network
  • 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
  • Free and user-friendly license terms

More information on the FP-AI-VISION1 STM32Cube function pack and to download the software visit the ST website at STMicroelectronics FP-AI-VISION1 software page.

* STM32 are registered and/or unregistered trademarks of STMicroelectronics International NV or its affiliates in the EU and/or elsewhere. In particular, STM32 is registered in the US Patent and Trademark Office.

The STMicroelectronics website address is www.st.com.
[Reprinted with kind permission from STMicroelectronics - Release Date, 7th December, 2020]