Advanced People-Counting IoT Sensor with Integrated AI Enables Digital Attendance Monitoring for Smart Buildings

Advanced People-Counting IoT Sensor with Integrated AI

To overcome the challenge of monitoring attendance in large spaces with multiple entrance points, STMicroelectronics and Schneider Electric have collaboratively integrated Artificial Intelligence (AI) into a high-performance people-counting sensor. The advanced IoT sensor combines the high expertise of ST’s AI group and the deep sensor-application expertise of Schneider Electric, thereby identifying and embedding a high-performing object-detection neural network in a small microcontroller (MCU).

 

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 prototype people-counting sensor combines LYNRED ThermEyeTM family thermal imager, integrated into a unique ultra-low-power design created by Schneider Electric, with a Yolo-based Neural Network model running on the recently introduced high-performance STM32H723 MCU. It opens a new solution for attendance monitoring and people counting in numerous applications such as monitoring queues, building usage, and social distancing.

 

The STM32Cube.AI ecosystem provides essential building blocks for neural networks to run on STM32 MCUs, enabling a cost-effective and power-efficient solution. It natively supports deep-learning frameworks like Keras, TensorFlow Lite, and ONNX exchange format, etc. The ecosystem includes the X-CUBE-AI software expansion package and extends the capabilities of the STM32CubeMX initialization tool to automatically convert pre-trained neural networks, generate optimized libraries for the target MCU, and integrate these into the user's project.

 

Key Features of the STM32 AI Ecosystem

  • Provides essential building blocks for neural networks to run on STM32 MCUs Enables cost-effective and power-efficient solution
  • Supports deep-learning frameworks like Keras, TensorFlow Lite, and ONNX exchange format
  • High core performance
  • Up to 1Mbyte Flash
  • High-speed off-chip memory interfaces
  • Comes with integrated features for connecting a wide variety of sensor types

 

The STM32H723 MCU offers high core performance, up to 1Mbyte Flash, high-speed off-chip memory interfaces, and integrated features for connecting a wide variety of sensor types.

Add new comment

The content of this field is kept private and will not be shown publicly.

Plain text

  • No HTML tags allowed.
  • Lines and paragraphs break automatically.
  • Web page addresses and email addresses turn into links automatically.