The collaboration has seen the two companies integrate Artificial Intelligence (AI) into a high-performance people-counting sensor, overcoming the challenges associated with monitoring attendance in large spaces with multiple entrance points.
The queue monitoring solution will assist in smart building management while respecting individuals’ privacy by design. The advanced IoT sensor has been developed by combining ST’s AI group's expertise with Schneider's extensive experience in developing deep sensor-applications, to identify and embed a high-performing object-detection neural network in a small microcontroller (MCU).
Schneider Electric’s use of the STM32Cube.AI toolchain, which is able to support the development of AI applications for the broad portfolio of STM32 MCUs, has helped it to gain much greater flexibility and efficiency in hardware design from the engineering resources and ease of use provided by the STM32Cube software-development ecosystem.
The prototype people-counting sensor combines a LYNRED ThermEye family thermal imager, integrated in an ultra-low-power design created by Schneider Electric, with a Yolo-based Neural Network model running on the recently introduced high-performance STM32H723 MCU from ST.
"This promising technology opens a new solution for attendance monitoring and people counting in numerous applications such as monitoring queues, building usage, and social distancing,” said Maxime Loidreau, IoT Sensors Program Manager at Schneider Electric.
“It demonstrates the power of deep learning to enhance embedded data-processing performance, showing how high-value applications can be hosted on a cost-effective microcontroller-based platform,” added Miguel Castro, AI Solutions Business Line Manager at STMicroelectronics. “Our STM32Cube.AI ecosystem empowers users to create flexible solutions within a fast time-to-market window.”
