Be visionary

November 28, 2018 // By Stephen Hayes
November’s Vision show in Stuttgart felt like a key moment of change for the industry. Four big themes came to fruition at the event, at least two of which felt like science fiction at the last Vision show in 2016. In fact, the show’s strapline, ‘Be Visionary’ has never felt so appropriate.  

With Beckhoff showcasing its TwinCAT Vision product at SPS Drives, now seems like a good time to explain the way the product fits into the themes that dominated the Vision show. In addition to the wider manufacturing landscape, which is still ruled by Industry 4.0. 

Vision 2018’s biggest themes were hyperspectral imaging, deep learning, autonomous machine vision (AMV) and embedded vision. The irony is that the objective of all these things, which sound pretty high-tech and high-concept, is to make things easier for the manufacturer applying the technology. When Steve Jobs was explaining the simplicity of the early Apple operating systems, he said, “Most people have no concept of how an automatic transmission works, yet they know how to drive a car.” In the same way, the core technology themes of Vision were focussed on ensuring that vision system users don’t need to understand the complexity of the device to reap its benefits.

 

Hyperspectral imaging

The goal of hyperspectral imaging is to obtain the radiance, or light intensity, for each pixel in the image of a scene creating a large series of continuous spectral bands, with the purpose of finding objects, identifying materials, or detecting processes. Historically the drawbacks have been a lack of computing power and sensor cost, but both issues have become less problematic as technology has advanced.

One of the businesses at Vision, a Finnish firm called Specim, is delivering hyperspectral solutions across the food, waste and recycling industries, improving accuracy and liability in detection of defects and parts. But this is just one of the ways that the vision market is transcending science fiction and moving into science fact.

 

Deep learning

Deep Learning allows industrial visions systems to be applied using a simple training process, removing the huge amount of effort and expertise that was traditionally associated with the integration process. Instead of months of crafting algorithms deep learning replaces this idea with simple training of the system. There was barely a stand at Vision 2018 which didn’t proudly proclaim that it had ‘inbuilt deep learning’ or ‘advanced AI’. But for those who have truly seized the baton, this will be a genuine game changer.


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.