MV systems in manufacturing to approach 100 million by 2025

Tech market advisory firm ABI Research has predicted that total shipments for machine vision sensors and cameras will reach 16.9 million by 2025, creating an installed base of 94 million machine vision systems in industrial manufacturing. Of that installed base, 11% will be deep learning-based.

Machine vision is a mature technology with established incumbents. However, significant advancements in chipsets, software and standards are bringing deep learning innovation into the machine vision sector. Such systems are a staple in production lines for barcode reading, quality control and inventory management.

“These solutions often have long replacement cycles and are less prone to disruption. Due to the increasing demands for automation, machine vision is finding its way into new applications,” said Lian Jye Su, Principal Analyst at ABI Research. “Robotics, for example, is a new growth area for machine vision: Collaborative robots rely on machine vision for guidance and object classification, while mobile robots rely on machine vision for SLAM and safety.”

A different breed from conventional machine vision technology, deep learning-based machine vision is data-driven and utilises a statistical approach, which allows the machine vision model to improve as more data is gathered for training and testing. Major machine vision vendors have realised the potential of deep learning-based machine learning. Cognex, for example, acquired SUALAB, a leading Korean-based developer of vision software using deep learning for industrial applications, and Zebra Technologies acquired Cortexica Vision Systems, a London-headquartered leader in business-to-business (B2B) AI-based computer vision solutions.

At the same time, chipset vendors are launching new chipsets and software stacks to facilitate the implementation of deep learning-based machine vision. Xilinx, an FPGA vendor, partnered closely with camera sensor manufacturer Sony and camera vendors such as Framos and IDS Imaging to incorporate its Versal ACAP system on chip (SoC). Intel, on the other hand, offers OpenVINO for developers to deploy pre-trained deep learning-based machine vision models through a common API to deliver inference solutions on various computing architectures. Another FPGA vendor, Lattice Semiconductor, focuses on low-powered AI for embedded vision through its senseAI stack, which offers hardware accelerators, software tools and reference designs.

On the standards front, vendors are bringing 10GbE and 25GbE cameras into industrial applications. Continual upgrades on video capturing and compression technologies also generate a better image and video quality for deep learning-based machine vision models. This ensures the futureproofing of machine vision systems.

“When choosing machine vision systems, end implementers need to understand their machine vision requirements, consider integration with their backend system, and identify the right ecosystem partners,” said Su. “Deployment flexibility and future upgradability and scalability will be crucial as machine vision technology continues to evolve and improve.”

The findings are from ABI Research’s report ‘Machine Vision in Industrial Applications’.

Image credit: ©stock.adobe.com/au/spainter_vfx