Sichere Elektrofahrzeuge

Bild 1 | Ein Roboterarm bewegt die Batterieabdeckung zum Kamerasystem (im schwarzen Kasten)

Die E-Mobility bringt immer effizientere Produktionsprozesse hervor, besonders durch die Kombination mit KI. Das gilt auch für die Metallveredelung, wie das Beispiel der TAS GmbH zeigt. Der Spezialist für Oberflächentechnologien setzt auf ein KI-basierendes Bildverarbeitungssystem von ID-Engineering / Zebra Technologies, das die Fehlerdetektion übernimmt – und sich kontinuierlich selbst verbessert.

Inspect Smart

Scan data for a shiny metal target with the Gocator 3000 snapshot sensors, which combine blue-LED structured light with built-in 3D measurement tools.

The trends in smart machine vision indicate a shift towards intelligent, integrated, and user-friendly systems. LMI Technologies is developing and deploying smart machine vision solutions through sensor, software, and AI-enabled vision technologies for the factory. The company described five trends to thrive in a changing landscape.

Der richtige Weg

Bild 2 | Inverse perspektivische Projektion

Immer mehr Kamerahersteller integrieren KI-Algorithmen direkt in ihre Kamerasysteme, damit Roboter komplexere Aufgaben bewältigen können, wie z.B. das Greifen von unstrukturiert vorliegenden Objekten. Damit diese gegriffen werden können, müssen sie zunächst erkannt werden. Anschließend wird eine Bahn ermittelt, die den Roboter zum Zielobjekt bewegt. In dem Beitrag des Fraunhofer IOSB-INA werden zwei Fallstricke beleuchtet, die Voraussetzung für die Güte dieser nachgelagerten Bahnplanung in einem realen Kamera-basierten Robotersystem sind.

Knock on Wood

Image 1 | Dralle's high-precision 3D technology enables all-weather, all-season, day and night, off-grid timber measurement.

Traditional manual timber stack measurement is a slow, manual, labor-intensive process, plagued by inaccuracy and safety risks for workers in harsh weather. Dralle A/S, a leader in forestry digital technology, faced critical limitations with their legacy timber stack measurement system. But their initial system, an x86 platform, couldn’t keep pace with modern AI demands, therefore the company partnered with Aetina.

Keep off the Pitch!

Image 1 | Agrowing's multispectral AI approach promises to elevate turf maintenance without ever setting foot on the grass.

Agrowings ambitious vision is to revolutionize the agricultural
industry by enabling definite aerial detection and identification of pests and diseases in open field crops through cutting-edge multispectral AI analysis.

Hyperspectral X-ray

Image 1 | XSpectra is the first hyperspectral inspection system in the food industry based on the photon counting technique, capable of performing real-time chemical and physical analysis of the product to identify foreign bodies currently undetectable by existing inspection technologies.

Xnext´s XSpectra is the first hyperspectral inspection system in the food industry based on photon counting technique, capable of performing real-time chemical and physical analysis of the product to identify foreign bodies. It performs analysis in milliseconds, exploiting up to 1024 energy levels of X-rays while competitors use a maximum of two.

Be Careful!

One of the mega trends currently is AI. In a panel discussion at the inVISION Day Metrology it was intended to address the question to what extent and where AI is already being used in metrology and what changes could result from the use of AI in metrology in the future. To discuss these topics, experts from Hexagon, VisiConsult and Zeiss were invited.