Neural Network Running on Industrial Standard SoM

AI on Industrial Standard SoM

AI / Machine Learning

Introduction

FPGA technology is becoming a major player in the field of embedded AI applications due to its ability to implement complex neural networks with low power consumption and low latency, while simultaneously interfacing a large number of peripherals and providing high levels of robustness, important for industrial applications.

Customer Challenge

In this case, Enclustra was their own customer. The challenge was to explore the potential of FPGAs in embedded AI applications and showcase it through a demo system.

The Solution

Based on the Mars XU3 module, featuring a AMD Zynq™ UltraScale+™ MPSoC device, mounted on the Mars ST3 base board, the application employs popular neural networks like resnet50 and SSD for image classification and real-time face detection, respectively. The images are captured with a standard USB camera, connected to the Mars ST3 base board. For higher performance a MIPI interface can be used, also available on the Mars ST3. The live image with added overlays can then be viewed on a DisplayPort-capable monitor. Moreover, adding actuators such as BLDC or stepper motors is a straightforward task using Enclustra’s Universal Drive Controller IP Core.

The Result

Enclustra successfully deployed an AI-powered embedded real-time image processing application to run on Enclustra’s own SoC Module, which now serves as a demo system.