Distracted driving remains a leading cause of road accidents, with even a brief glance at a phone potentially resulting in fatal consequences. Autotrak, a fleet management specialist, has taken on this challenge by developing an innovative AI-powered camera system designed to prevent distracted driving and make roads safer for everyone.

Challenges

Designers of real-time driver monitoring systems have long faced a difficult trade-off: either invest in expensive processing solutions that increase the overall cost or rely on affordable cloud-based computing, which often cannot deliver the real-time decision-making required for safety-critical applications. Additionally, creating a solution that is both cost-effective and robust enough to operate reliably in the demanding environment of a vehicle, especially under high temperatures, has proven challenging.

Approach

Autotrak addressed these challenges by leveraging the STM32N6 microcontroller (MCU), the first MCU with integrated AI acceleration. This breakthrough enabled Autotrak to deliver microprocessor-like performance in a compact, embedded system. The STM32N6’s embedded image signal processing (ISP) allowed Autotrak to extract high-quality images from a medium-resolution camera without resorting to more expensive hardware. Its advanced AI image classification capabilities enabled the system to analyze and categorize millions of driver gesture images in real time, directly on the device.
 
The STM32N6’s resilience to high temperatures made it possible to mount Autotrak’s advanced driver-assistance system (ADAS) on the vehicle’s windscreen, ensuring reliable performance in harsh conditions. Furthermore, the built-in neural processing unit, known as the Neural-ART Accelerator, and the ST Edge AI Suite provided developers with powerful tools for model optimization, code conversion, and deployment. This comprehensive support enabled Autotrak to rapidly prototype and launch their solution in under three months, all while maintaining a focus on customer safety.

The STM32N6 MCU has enabled us to develop a cost-effective, compact, low-power ADAS solution that operates at high temperatures, unlike traditional MPU solutions.

Gavin Leask, Engineering Director, Autotrak

By combining the unique capabilities of the STM32N6 MCU and edge AI technology, Autotrak has created a real-time, cost-effective, and robust driver monitoring system that helps prevent distracted driving. Their solution not only enhances road safety for truck drivers and fleet employees but also demonstrates how innovative edge AI can overcome longstanding challenges in automotive safety technology.

Author: Autotrak, ST | Last update: June, 2025

Optimized with

STM32Cube.AI
STM32Cube.AI

Most suitable for

STM32N6 Series

Most suitable for
Resources

Optimized with STM32Cube.AI

A free STM32Cube expansion package, X-CUBE-AI allows developers to convert pretrained AI algorithms automatically, such as neural network and machine learning models, into optimized C code for STM32.

Optimized with STM32Cube.AI Optimized with STM32Cube.AI Optimized with STM32Cube.AI

Most suitable for STM32N6 Series

The STM32 family of 32-bit microcontrollers based on the Arm Cortex®-M processor is designed to offer new degrees of freedom to MCU users. It offers products combining very high performance, real-time capabilities, digital signal processing, low-power / low-voltage operation, and connectivity, while maintaining full integration and ease of development.

Most suitable for STM32N6 Series Most suitable for STM32N6 Series Most suitable for STM32N6 Series
You might also be interested by

Vision | STM32Cube.AI | STM32 AI MCU | Video | Customer | Accelerometer | Wearables

How ultralight AR glasses are redefined with Edge AI

Meta-Bounds elevates AR glasses with STM32N6 MCU edge AI and computer vision technology

Industrial | Partner | STM32 AI MCU | STM32 MCU | Vision | Agriculture | STM32Cube.AI

How Edge AI helps avoid bird collisions with wind turbines

Protecting biodiversity with embedded computer vision for real-time detection and prevention

Industrial | Smart city | Vision | STM32Cube.AI | STM32 AI MCU | Partner | Video | Transportation | Model zoo

Smart rear view camera running on batteries

How does the STM32N6 improve real-time detection of people, cars, trucks, and cyclists in blind spots