Gesture recognition Deep Learning project for STM32 (based on Keras model)
Deep Learning project inspired by DeepGesture project (https://github.com/GwangsHong/DeepGesture) and adapted to fit 32-bit microcontroller STM32 for real time and low power application.
Published Keras model with small dataset used for initial validation, soon it will follow FW project for STM32L4 and complete documentation of the project.
Dataset collected with Sensortile evaluation board of STMicroelectronics: (https://www.st.com/content/st_com/en/products/evaluation-tools/solution-evaluation-tools/sensor-solution-eval-boards/steval-stlkt01v1.html).
FW porting from Keras to C code for STM32 done using STM32CubeMX.AI tool: (https://www.st.com/content/st_com/en/products/embedded-software/mcu-mpu-embedded-software/stm32-embedded-software/stm32cube-expansion-packages/x-cube-ai.html).