Deeplite and E-Smart Case Study – Faster AI for Advanced Driver Assista



The mass shift to e-commerce has highlighted the critical role of freight trucking within the world economy as the volume of goods delivered daily to businesses and consumers soars. According to estimates from Research and Markets, the global freight trucking market is forecast to reach $5.5 trillion by 2027, with the US alone accounting for roughly 20% of the total market.For companies with large fleets of trucks, managing the safety of their drivers, cargo and bystanders along delivery routes has always been a top priority, but now there is smart technology to enable it automatically.

Based in Indianapolis with operations and customers in the United States, Canada and Mexico, E-SMART develops and manufactures innovative software solutions that offer fleet managers the ability to significantly improve vehicle safety while also reducing fuel consumption.


As an industry leader in intelligent speed management solutions, E-SMART faced a critical roadblock in rolling out its latest innovation to customers: a computer vision algorithm that goes beyond existing speed ‘warning’ technologies to actively control a vehicle’s speed.

Using a camera connected to E-SMART’s Advanced Driver Assistance System (ADAS), the company’s AI model was trained to recognize speed limit signs in real-time and automatically adjust a truck’s speed to below the limit for safety. The new technology would enable drivers and fleet managers to achieve industry-leading safety standards while also improving operational efficiency. It was a high priority for E-SMART and its customers.

“We’re focused on finding innovative ways to respond to our customers’ needs, and proactive safety is a big one. According to the US DOT, 30% of all accidents are speed-related, and 70% of fatal crash accidents happen on non-interstate roads. While basic governors can limit top speeds to 60, 65 or 70, we wanted a proactive system that could recognize and not exceed the speed limit of any road,” said Mathieu Boivin, President & CEO of E-SMART.

The challenge for E-SMART was that computer vision software is typically large and complex, requiring expensive, power-hungry graphics processing units (GPUs) to operate effectively. As a result, it was unclear how the active speed control technology could be deployed in newly-built systems – not to mention the thousands of vehicles already in the field with legacy, resource-constrained CPUs – while maintaining the cost-efficient standards that E-SMART’s customers counted on.


To avoid the time and expense required to upgrade hardware across customers’ fleets, E-SMART instead looked for ways to maintain the accuracy of its AI model while optimizing it to run on the existing hardware already in its customers’ trucks and turned to Deeplite and its Neutrino™ AI optimization software.

Deeplite’s Neutrino uses AI to make other AI models smaller, faster, and more energy-efficient at the edge and in other resource-constrained environments. E-SMART partnered with Deeplite to dramatically reduce the size of its YOLOv3 PyTorch computer vision model so it could be deployed to existing ADAS systems.

After training E-SMART’s Convolutional Neural Network (CNN) to the acceptable level of performance (mAP) to recognize speed limit signs from the LISA data set and the ability to run on various hardware to maximize deployment flexibility, Deeplite delivered the following optimization benefits:



Through state-of-the-art optimization techniques, Deeplite achieved exceptional results while maintaining E-SMART’s desired level of accuracy.



With the ability to optimize large, complex AI models and computer vision solutions to run on its existing ADAS hardware, E-SMART plans to work closely with Deeplite to create innovative new solutions that expand the capabilities of its ADAS platform to create further value for fleet managers.

Added Boivin, “As the transportation market accelerates toward smart, tech-assisted and eventually autonomous vehicles, partnering with Deeplite will turn our vision of proactive speed control and other new technologies into a reality for fleet managers. With Deeplite, we are delivering cutting-edge tech to our customers at a price point that is highly accessible. It’s a win for everyone.”