synthetic training data for machine vision.

Imagine a pipe inspection robot. How do you train its vision algorithm when neither the robot nor the piping network has been built yet? In other use cases, some real-life data may be available, but the dataset is imbalanced, critical edge cases are missing or annotation is lacking. A large set of diverse, well-annotated and relevant data is key to developing a successful machine learning algorithm. Synthetic training data offers a solution where this data is not available or incomplete. Demcon develops project-specific simulations which generate near-infinite permutations of specific 3D environments. These environments are sampled by a range of virtual sensors to generate rich, well-balanced datasets.


  • Digital Twin of project-specific 3D environment generates rich datasets and annotation
  • Procedural methods create near-infinite permutations of objects and environments
  • Pixel perfect annotation
  • Simulation of a range of sensors, e.g. RGB(D), infrared, Lidar, et cetera
  • Rare edge cases can be generated at will to balance the dataset
  • Enables Machine Learning where data or accurate annotation is not obtainable
  • Develop in silico: digital twin of environment, device and sensors

Business Manager Demcon Synthetic Data

Vincent Bos.

“Synthetic data is an exciting new field with great possibilities. The application of our technology enables the use of machine learning where it would otherwise be limited by a lack of good data. “

a known ground truth provides perfect annotation.

A simulation provides a known ground truth, enabling rich, pixel-perfect annotation. This includes annotation which is typically very hard or impossible to do, such as segmentation, depth, surface normals, optical flow, consistent quality indicators on a per-pixel or per-object basis and much more.

variation beyond the basics.

Demcon develops procedural models and methods to construct our project-specific environments. This means our models include methods that are developed to enable variation beyond basic parameters such as color, size and orientation.

Organic subjects such as fruits and vegetables are inherently difficult to capture due to their large natural variation. Our approach is not to model a great number of different models but to develop one procedural model. The parametric interface to these procedures enables the generation of near-infinite variations by varying e.g. shape parameters, age and defects. By linking distributions of parameters, we can develop high-level interfaces to generate random instances of fruit of arbitrary classifications or quality levels. This allows for annotation of highly consistent quality indicators on both a pixel-level and an object-level throughout the system.







Generate near-infinite permutations and pixel-perfect annotation. ”

all expertises.


data science & machine learning

The vast domain of AI is rapidly entering the high-tech industry…

Read More


In electronic and electrical engineering, we develop multidisciplinary solutions for …

Read More

industrial design

In high-tech product development, industrial design engineering revolves …

Read More


High-end product and system development heavily relies on prototyping and manufacturing ..

Read More


In mechanical engineering, we push the boundaries of what is physically feasible. Time …

Read More


Mechatronics embodies the integration of mechanics, electronics, software and control…

Read More

optics & vision

High-tech and industrial system development often relies on proper optics and vision …

Read More

quality & regulatory compliance

When developing high-tech products and systems, it must …

Read More

software architecture & design

In our multidisciplinary systems engineering approach, software …

Read More

systems engineering

A high-tech development project starts with fundamentally understanding the customer’s …

Read More