• Nederlands

Solution

Point cloud analysis

Recognising and classifying objects in 3D point clouds from scans and sensors, so inspection and measuring work that is now done by hand can run automatically.

Get in touch →
Laser scanner on a tripod in the middle of a bright office floor

From point cloud to judgement

A 3D scan delivers millions of loose points, and no answer. Between the scan and a decision sits interpretation: which object is this, is the shape right, is the deviation within tolerance? In many production environments that work is still done by hand.

What the analysis does

  • Recognise and classify objects in the point cloud.
  • Spot shape deviations and defects, against the standard you set.
  • Feed the outcome back to the line, so it can be corrected.

Where it fits

Wherever 3D measurements come in faster than people can assess them: inspection in production lines, checking parts in automotive and manufacturing. The approach connects to the scanners and systems already in place: the assessment standard stays yours.

Related work: CAD/CAM automation and the project AI for Lightweight Construction.

What you get

Not a package, but a working solution

Twentynext is not a software vendor. We investigate the question, design the solution and build it until it runs in production.

What we deliver

A solution that runs in your own process, on your own data. No licence for someone else’s software, and no report with recommendations.

Where we start

With the business question, not with the model. Which decision needs improving, and what information does it depend on? Technology is the last step, not the first.

Who builds it

The same people who design it. From data analysis and architecture to production and management, without handing over to another party.

Frequently asked questions

What is point cloud analysis?

A 3D scan delivers millions of loose points, and no answer. Point cloud analysis is the interpretation of those points: which object is this, is the shape right, is the deviation within tolerance? In many production environments that work is still done by hand.

What does the analysis actually do?

Three things. Recognise and classify objects in the point cloud. Spot shape deviations and defects, against the standard you set. And feed the outcome back to the line, so the process can be adjusted.

Does this work with the scanners we already have?

The approach connects to the scanners and systems already in place. The work sits in interpreting what those scanners deliver.

Who decides what counts as a deviation?

You do. The assessment standard stays yours; the analysis checks every measurement against it.

Where does it fit?

Wherever 3D measurements come in faster than people can assess them: inspection on production lines, checking parts in automotive and manufacturing.

Is this the same as CAD/CAM automation?

No. CAD/CAM automation generates designs within hard requirements; point cloud analysis assesses measurements of existing objects against a standard. Related work is described under CAD/CAM automation and the project AI for Lightweight Construction.

Example of a scan result: spider chart with four dimensions

Where does your organisation stand?

Sixteen questions, seven minutes, and an instant spider chart showing your strongest and weakest dimension. No e-mail address needed to see the result.

Work with us

Realise your project together?

The people who build it also run it afterwards. Eindhoven, since 2014.

Martijn van Grieken

Martijn van Grieken

Director Data & AI

Book an introduction or ask a question first