New configurable AI-powered 3D machine vision from SICK combines deep learning with precise height data analysis via its Nova foundation software. The industrial automation and sensor intelligence specialist has equipped its Nova machine vision platform with AI deep learning algorithms to enable ease of use and quick customisation, opening up a range of new capabilities.
Combining AI with spatial understanding, AI-powered 3D image processing goes beyond conventional 3D imaging to include more advanced inspection functions. It is the first time SICK has provided intelligent AI capabilities for its high-precision 3D machine vision technology and its Nova Intelligent Inspection toolset.
Delivering configurable 3D machine vision in sectors such as logistics, electronics, battery manufacturing, automotive and consumer goods, AI for 3D with SICK Nova improves quality control with intelligent inspection. The example-based approach, together with on-device training and a user-friendly interface, simplifies solution development and provides a cost-efficient way of incorporating deep learning into quality control operations, with no extra equipment required.
New applications across an array of industry sectors
SICK AI-powered machine vision with 3D height analysis unlocks advanced quality control applications that were previously difficult or impossible to achieve with traditional rule-based inspection. Key applications for the new solution include the following:
• Package deformation inspection in sectors such as food and beverage and consumer goods.
• Empty box and missing object detection in totes or matrix packaging for fulfilment and logistics operations.
• Assembly verification and surface inspection for electronics and battery production.
• Classification and tyre inspection, including 3D optical character recognition, for automotive applications.
• Completeness checks in manufacturing.
AI-powered deformation inspection, for example, validates the appearance, integrity and function of carton packaging after filling, reliably measuring height deviations of the shape and surface of packages to detect defects at high speed, even where there is no colour contrast. AI-powered 3D machine vision removes faulty products from the production and packaging process at an early stage.
AI for 3D with SICK Nova foundation software
Teach-by-example with sample images provides easy setup, and SICK’s AI for 3D solutions are customised and trained on each organisation’s own data. Users collect data, train models, and execute inspection tasks directly on-device with reliable, quick setup of inspection tasks that enables fast, effortless batch changes.
Every pixel carries a height value and is captured by accurate, high-precision SICK technology, enabling reconstruction of 3D data and defect detection by a trained neural network embedded in the Nova AI software. The new solution provides colour- and contrast-independent inspection and improved quality control, with detected defects displayed on an anomaly heatmap. Activated with a licence on pre-defined devices or through an upgrade licence, the toolset also includes traditional rule-based machine vision software tools.
SICK experts work closely with customers to develop tailored solutions that address key inspection challenges and detect specific anomalies, from minute electrical components to large packaged goods.
“For SICK, innovation is our driving force,” says Diego Quintana Tukasaki, market product manager at SICK. “Together with our customers and partners, we transform challenges into solutions. Our latest innovation combines SICK quality, expertise and consistency with deep learning to meet demand in two of the highest-growth product categories in machine vision: AI software and 3D imaging. Introducing neural network AI capabilities into our high-performance Nova platform expands 3D inspection beyond its traditional limits, providing greater control over data, and analytics to deliver highly accurate, configurable and easy-to-train intelligent inspection solutions.”
| Tel: | +27 10 060 0550 |
| Email: | [email protected] |
| www: | www.sick.com/za/en/ |
| Articles: | More information and articles about SICK Automation Southern Africa |
© Technews Publishing (Pty) Ltd | All Rights Reserved
printer friendly version