At the event, attendees will have the chance to see how manufacturers, including those in the automotive, food and beverage, and packaging industries, can equip their engineers, programmers, and data scientists with versatile deep learning machine vision solutions. These solutions are designed to operate across various platforms, including devices, PCs, at line-side, and across multiple factory locations.
“The latest and best deep learning machine vision systems also need the best implementation options for ease of use,” said Donato Montanari, Vice President and General Manager, Machine Vision, Zebra Technologies. “Manufacturers can develop more connected factories and collaborative teams with deep learning, from ready out-of-the-box tools for the non-specialist to advanced toolsets for data scientists.”
According to Zebra’s 2024 Manufacturing Vision Study, 54% of manufacturers in Europe (and 61% globally) expect AI to be a key driver of growth by 2029. Currently, 36% of manufacturers are using deep learning for process automation, with 63% planning to adopt it within the next five years.
Zebra's booth at VISION 2024 will feature over a dozen demonstrations of machine vision hardware and software, highlighting the flexibility and capabilities of its extensive portfolio. Attendees will be able to explore and interact with Zebra’s Aurora software suite. Other demonstrations include PC-based and FS42 camera-based deep learning optical character recognition, anomaly detection on smart vision sensors, and a conveyor demo using Aurora Vision Studio. Additionally, there will be 3D sensing demonstrations using Zebra’s 3S Series 3D sensors and AltiZ devices paired with Aurora software for 3D inspections.
Throughout the event, Zebra’s machine vision experts will provide video updates from the booth, which can be viewed on LinkedIn at 16.00 CET (10.00 EST).
Donato Montanari will also deliver a presentation titled "The Cloud Will Deliver End-To-End AI Solutions for Machine Vision Users," discussing the benefits of integrating cloud solutions to enhance deep learning machine vision systems.
“A Cloud approach would enable a rich and diverse data pool from across sites that could be labelled and annotated, and deep leaning models trained, with users having access to new collaboration tools and the latest computing resources,” said Montanari. “Such a platform opens up true end-to-end AI solutions with model Edge deployment on PCs and devices to support flexible, digitised workflows on the production line, on a PC or device wherever a user or team is located.”
