First AI-powered industrial cameras for Industry 4.0
Neurala, a specialist in vision AI software, together with FLIR Systems have developed a full software and hardware stack AI-based industrial imaging solution.
Neurala’s vision AI software makes it possible to deploy deep learning with no-AI-expertise-required, and supports the creation of neural networks that can be deployed directly onto FLIR Firefly DL cameras. A developer of machine vision cameras, FLIR’s Firefly DL cameras are compact and come with built-in inference on the edge capabilities.
Through the collaboration, Neurala and FLIR are looking to deliver a faster, more cost-effective entry point for customers looking to deploy deep learning on the production line and comes at a time when manufacturers are focused on AI and automation to provide flexibility to cope with production constraints, supply chain disruptions, and scattered workforce availability.
The solution allows customers to rapidly create deep learning models using Neurala’s Brain Builder on the VIA platform with little data and no AI expertise. These models can be directly uploaded to a FLIR Firefly DL camera using the free FLIR Spinnaker SDK. As a consequence, neural networks can be deployed for a wide variety of applications, including printed circuit board (pcb) inspection, detection of foreign objects, identification of surface level metal defects and product uniformity issues.
The ability to deploy directly onto the compact FLIR Firefly DL camera means that an intelligent, automated inspection point can be placed practically anywhere in-line and quickly reconfigured for new applications.
“The rise of Industry 4.0 has challenged manufacturers to rethink the tools and systems they are using as part of their workflow. With cameras and sensors gathering product data and analyzing the overall health of industrial equipment, manufacturers have realized the power of AI to draw actionable insights from this data,” said Max Versace, CEO and co-founder of Neurala.
“Being one of the world’s first machine vision manufacturers with an inference on the edge solution, we are constantly looking for ways to help our customers stay at the cutting edge,” said Sadiq Panjwani, Vice President, components Business, FLIR Systems. “Our collaboration with Neurala on a simplified and accessible full-stack deep learning solution is another step in that direction, bringing customers the advanced machine vision techniques required for today’s highly automated industrial environments.”