FP-AI-VISION1 is an STM32Cube function pack featuring examples of computer vision applications based on Convolutional Neural Network (CNN).
FP-AI-VISION1 is composed of software components generated by the X-CUBE-AI Expansion Package complemented with application software components dedicated to the AI-based computer vision example for food recognition.
FP-AI-VISION1 enables advanced computer vision application on the basis of outputs generated by Neural Networks (NNs). The NNs are implemented by libraries generated by the X-CUBE-AI Expansion Package for the STM32CubeMX tool.
The examples provided in the function pack are food recognition applications based on a CNN derivated from MobileNet CNN. They recognize among 18 classes of common food such as pizza, hamburger, and Caesar salad.
The function pack demonstrates two different integrations of the food recognition application: one is based on a floating-point model, and the other one on a quantized model generated by the quantization tool featured by X-CUBE-AI.
The function pack features some libraries to debug and validate the embedded application.
FP-AI-VISION1, together with the suggested combination of HW boards, is used to develop specific computer vision applications: it includes the drivers for the camera as well as the framework for capturing images into the frame buffer, pre-processing the content of the frame buffer, and running the Neural Network inference.
FP-AI-VISION1 runs on the STM32H747I-DISCO Discovery board connected to the STM32F4DIS-CAM camera daughterboard through STMicroelectronics DCMI parallel interface. Information related to STM32H747I-DISCO is available on STMicroelectronics website at www.st.com while information about STM32F4DIS-CAM is obtained directly from Farnell website at https://www.farnell.com.
- 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) generated by means of the X-CUBE-AI Expansion Package for STM32CubeMX
- Food recognition applications based on Convolutional Neural Network model (MobileNet CNN model derivative)
- Integration examples based on float and quantized models
- Libraries enabling the test, debug and validation of the embedded Neural Network application
- Support for camera frame capture to enable image dataset collection
- Sample implementations available for the STM32H747I-DISCO Discovery board connected to the STM32F4DIS-CAM camera daughterboard
- Free, user-friendly license terms
|Part Number||General Description||Software Version||Supplier||GitHub link||Download|
|FP-AI-VISION1||STM32Cube function pack for high performance STM32 with artificial intelligence (AI) application for Computer Vision||1.1.0||ST||-|
MadeForSTM32™ is a new quality label delivered by ST, which is granted after an evaluation process. It helps engineers identify third party solutions with the highest level of integration and quality for the STM32 microcontrollers' ecosystem. MadeForSTM32™ is offered to members of the ST Partner Program who want to go one step further in our collaboration, with the overall objective of contributing to a high-quality STM32 ecosystem.
The STM32Cube.AI is an extension pack of the widely used STM32CubeMX configuration and code generation tool enabling AI on STM32 Arm® Cortex®-M-based microcontrollers.
The X-CUBE-VS4A Expansion Package consists of a set of libraries and application examples for STM32F7 Series microcontrollers acting as Alexa-enabled devices. It runs on the 32F769IDISCOVERY board, which provides a native Ethernet interface.