I'm trying to implement a detection model on a STM32-H747i-disco board, the only example provided is the one called "people counting", but the libraries are provided in binary format and it seems that it is not possible to modify them.
How could we implement a detection model to detect specific objects (such as cars) ? Or is it possible to fine tune an existing detection model ?
Thank you for your help,
Hello @Raphaël SOLER and welcome to STCommunity 🙂,
I think that the PersonDetection/Google_Model example in FP-AI-Vision1 package can help you.
This application demonstrates an example of image classification running on the STM32H7xx devices.
The image classification process is based on a convolutional neural network. The corresponding C model is generated using X-CUBE-AI v6.0.0 tool.
Also I recommend you to take a look to UM2526, this user manual provides the guidelines to build step by step a complete Artificial Intelligence (AI) IDE-based project for STM32 microcontrollers.
I hope this help you!
When your question is answered, please close this topic by choosing Select as Best. This will help other users find that answer faster.
To give better visibility on the answered topics, please click on Accept as Solution on the reply which solved your issue or answered your question.
Thank you for the welcome on the ST forum 🙂
I can already run a classification model by modifying the PersonDetection model. My question was about the implementation of an object detection (With Bounding Box) to recognize vehicles using an STM32H747I-Disco. The only example is People Counting from the FP-AI-VISION1 pack but the libraries are in binary format.
Is it possible to get the people counting example with an uncompiled library? An example project or a tutorial allowing to deploy an object detection (With Bounding Box) from our own model?
Thanks for your help,