MVTec Software GmbH

3D Registration & Perspective Matching

Featured in HALCON

3D Registration

3D sensor determining the shape of an object
Using 3D registration, the three-dimensional object shape is determined from multiple views with a 3D sensor.
3D shape of an object identified with 3D registration
The three-dimensional object shape is determined with 3D registration.

3D sensors directly capture the 3D coordinates of the visible points on the object surface. Using multiple 3D images of the object acquired from different points of view, the pairwise overlap of the 3D data is computed and a globally optimized shape is derived.

This technology is particularly suitable for 3D reconstruction, i.e. determining the 3D shape of arbitrary objects. The 3D object shape can be used in 3D matching, for quality inspection of 3D objects, or for the position recognition of 3D objects.

Our software packages support the direct derivation of the 3D object shape from 3D sensor data using 3D registration. Furthermore, our software offers advanced 3D shape processing techniques like smoothing, subsampling, and triangulation to prepare the shape model for 3D matching and object comparison.

Surface Fusion For Multiple 3D Point Clouds

Surface fusion for multiple 3D point clouds
Surface fusion

HALCON offers a method that fuses multiple 3D point clouds into one watertight surface. This method is able to combine data from various 3D sensors, even from different types like a stereo camera, a time of flight camera, and fringe projection. This technology is especially useful for reverse engineering.

Perspective Matching

A camera determining the 3D pose via a planar part of the object
Only a planar part of the object is necessary to determine the 3D pose of the object by exploiting perspective matching techniques.
Determining the 3D pose of five objects by finding the trained deformable model
Calculating the 3D pose of objects by finding the trained deformable model.

Instead of using the full 3D shape of an object, for many applications it is possible to restrict the model area to a planar part of the object. For arbitrarily shaped object parts, perspective matching allows to determine the 3D pose with only one camera. The model generation is done by training a sample image of the object typically inside a specified ROI.

Applications for this technology can be found within 3D alignment, e.g., applications for which the 3D pose (position and orientation) of an object must be found. Examples for such would be automotive and robotics applications, pick-and-place applications, and bin picking. A further possibility is the measurement of geometric features on complex 3D objects after 3D alignment.

Our software's perspective matching helps finding objects easily with only one camera. For perspective matching, our software packages provide two different methods suitable for two different classes of objects. Depending on the object's shape and appearance, our software offers both deformable matching, which is based on the shape-based matching technology (object edges), and descriptor-based matching, which uses so-called interest points.

Read Success Stories about 3D Vision


Fast automated inspection of seals through 3D vision with HALCON

Brett Martin is a producer of different plastic solutions like, amongst others, push-fit products in the area of plumbing and drainage. They hired Fis...


Bin-picking application with MVTec HALCON boosts productivity

Short cycle times, little scrap, minimal stock-keeping – the factory of the future is networked and highly economical. This requires increasingly...


Fully automated dispense and labeling system for pharmaceutical products runs with MVTec HALCON

MVTec’s Certified Integration Partner Crave Technical developed a vision system for an automatic unit-of-use dispense and labeling system for...


MVTec HALCON controls linear conveyor and robot system for fully automatic assembly of components

The complexity of the automation technology is constantly growing. On the one hand, this is due to the increasing variety of parts, and on the other...


The sweet pepper robot SWEEPER detects and picks ripe crops using MVTec HALCON

The Wageningen University & Research (WUR) in the Netherlands developed a greenhouse harvesting robot, which is able to pick ripe crops. The shape-...

Automotive & Robotics

Science Project: Proprioceptive Industrial Robot Gripper – Kinemetrix

Kinemetrix, based in Lexington, KY, specializes in advanced solutions for robotic automation. This spring, they supported a team of high school...


3D Vision Guided Robotic Assembly - Kinemetrix

Using HALCON's surface-based 3D matching technology and 3D point cloud data, the position and orientation of parts on an automated clip assembly cell...


Completely under Control: Bin-Picking-System Allows for Better Efficiency in the Production of Differential Gears - Jtekt Torsen

This article only exists as German version. To read the article in German, please follow this link.

Automotive & Robotics

Vision Helps Spot Failures on the Rail - Network Rail Ltd.

An automated vision inspection system relieves rail workers from the task of manually inspecting rail infrastructure


Vision Q.400 – The Universal Inspection Software for Industrial Image Processing

The software package Vision Q.400 from Q.VITEC was first created 20 years ago in cooperation with MVTec. Since this time, it has been continuously...