Success Story

Fully automated inspection of underbody trays with machine vision

Due to their intricacy, traditional inspection processes are often conducted manually and limited to spot checks. But Vista Solutions Inc. with offices in Canada, the US and Mexico has developed a breakthrough solution that changes that: the Flex-Inspect Platform. This automated inspection system leverages advanced machine vision to perform comprehensive measurements of automotive underbody trays – enhancing both accuracy and throughput. The machine vision software powering this platform is MVTec HALCON, developed by Germany-based MVTec Software GmbH.
HALCON
Automotive
Machinery
3D Vision
Inspection
Matching

From sci-fi to shopfloor: turning advanced vision concepts into real-world applications

Technologies like Surface-Based Matching, Sheet-of-Light, and Edge Extraction may sound like science fiction, but they’re revolutionizing industrial automation today. These machine vision technologies are essential of Vista’s solution for the automotive sector, where precise, high-volume inspections are mission critical.

The system conducts True Position Measurements (TPM) on key features of underbody tray assemblies. 2D cameras mounted to robotic arms capture images of relevant inspection points. These images are then analyzed by MVTec HALCON, which performs detailed measurements – such as width, depth, distance, and thickness – of critical part features. HALCON also assists with robot path planning to ensure optimal camera positioning for each inspection.

The result is a fully automated quality assurance process that hasn’t existed on the global market until now. Founded in 2003 and headquartered in Windsor, Ontario – with offices in Detroit, MI and Querétaro, Mexico – Vista Solutions develops turnkey machine vision systems for the automotive, road safety, and defense industries. Their portfolio includes consulting, implementation, and end-to-end customer support.

Machine vision: a quiet powerhouse in automotive manufacturing

Machine vision has become a key driver of automation in manufacturing, often described as a “hidden champion.” Why? It provides unmatched scalability, precision, and 24/7 uptime. Unlike human inspectors, vision systems don’t tire, vary in performance, or require breaks – making them ideal for repetitive inspection tasks.

In Vista’s case, the Flex-Inspect Platform was developed as an inline inspection solution for an automotive supplier, replacing a previously manual process. The objectives were clear:

  • Achieve 100% inline inspection for consistent, real-time quality validation
  • Reduce inspection time to fit within the production cycle
  • Free up skilled workers for higher-value tasks

“A machine-vision-based system was the only viable option to meet these goals,” explains Peter Denzinger, Vice President of Engineering at Vista. “Vision systems offer exceptional flexibility, rapid deployment, and, unlike sensors, they remain reliable even when positioning isn’t perfectly consistent.”

Automated inspection in action: robots, cameras, and deep image analysis

Built around MVTec HALCON, Vista’s Flex-Inspect Platform integrates a robust hardware setup: two 6-axis robots, each equipped with a 3D snapshot imager. These imagers combine industrial cameras with ring lights and laser projectors, enabling the creation of detailed 3D images of the part surface.

HALCON is deeply embedded in Vista’s control software and performs multiple core functions – starting with hand-eye calibration. This process aligns the coordinate systems of the robot and the vision system, a prerequisite for accurate part localization and measurement.

HALCON’s powerful operator library – comprising over 2,100 image processing tools – was a key factor in Vista’s software selection. “We’ve been working with MVTec since 2008,” Denzinger says. “For this project, HALCON offered the breadth of functionality and platform independence we needed.”

Once the underbody tray is positioned within the robotic work cell, both robots independently navigate to predefined measurement points. The system determines the real-world position of each datum and critical feature to execute TPM checks. The result is a clear pass/fail output, based on whether each measurement falls within acceptable tolerance limits.

To meet the tight cycle times required by modern production, each image must be processed as a snapshot in real-time.

Advanced image processing – from pixel to precision

What role do techniques like Surface-Based Matching, Sheet-of-Light, and Edge Extraction play?

  • Surface-Based Matching robustly and precisely identifies the relevant object within the camera’s field of view, forming the foundation for further analysis.
  • Sheet-of-Light enables accurate 3D surface reconstruction by calculating height profiles using laser lines, which are then merged with 2D images to create high-resolution 3D profiles.
  • Edge Extraction detects object boundaries at sub-pixel accuracy by identifying abrupt changes in image brightness or color – essential for reliable part feature definition.

These operations are repeated for every key feature of the part. Once all features have been measured, the system can perform fixture-based measurements or calculate 3D offsets for alignment and guidance purposes.

“HALCON’s extensive library allows us to select the best-fit method for each task,” says Jan Gärtner, HALCON Product Manager at MVTec. “That flexibility is crucial for manufacturers who need a system that can scale and adapt to a wide range of applications.”

Delivering real business value through automated quality

Vista’s solution has already been deployed for a full production cycle and has exceeded customer expectations. “We stayed in close contact with the client post-implementation and made sure that all strategic targets were hit,” says Denzinger. “The improved and consistent part quality gives them a clear competitive edge.”

Looking ahead, Vista and MVTec see increasing demand for intelligent inspection solutions – especially in automotive manufacturing, where AI-driven vision applications are poised to grow. “With the Flex-Inspect Platform and HALCON, we’re well-positioned to support that evolution,” adds Denzinger. 

Gärtner agrees: “Vista’s solution is a great example of how machine vision can create measurable value. By automating inspection, companies not only improve consistency and throughput – they also reduce labor strain and gain flexibility. It’s a clear win across the board.”

Further articles

Visualize Object Model 3D
Improve your surface-based matching with two helpful features
Do you sometimes have objects, which have rather small symmetry-breaking elements (such as small boreholes on an object)? Does your surface-based 3D matching not find the correct orientation?
Read more
Developers Corner
Deep OCR Interface
Deep OCR recognition training – the next level
HALCON’s Deep OCR is very powerful and can detect and recognize text in various industrial scenes. However, what if you have a special font, or want to read foreign characters? With HALCON 22.05 it is possible to train the recognition model to read s…
Read more
Developers Corner
Fitted primitives distance threshold
Metrology Model – Quality of Fit
"For most applications, the standard parameter values are sufficient." This sentence is often read in the HALCON Solution Guide. But what if the results do not meet your expectations? The Metrology Model allows lightning-fast measurement of geometric…
Read more
Developers Corner
Review of Acquisition Modes
This article gives an overview of HALCON’s image acquisition modes, explaining how continuous, triggered, and synchronous acquisition work, and clarifying common misconceptions for practical applications.
Read more
Developers Corner
Deep OCR – Tips and Tricks
Have you already experienced the performance boost by using Deep OCR compared to the classical rule‑based approaches? In this article, we’ll show you practical tips and tricks to further improve your Deep OCR results.
Read more
Developers Corner
Easy text and code reading with MERLIC standard tools
If you want to build an MVApp that reads for example QR codes or bar codes you can do so with just a few clicks. You can even combine the tools to get all available information printed on a product in different formats without the need for programmin…
Read more
Developers Corner
About MVTec's Heatmap
Imagine you intend to deliver a HALCON deep-learning-based classification application. And you are about to evaluate a trained model. You are therefore looking for feedback about this model, i.e. about its performances, biases, and other possible def…
Read more
Developers Corner
Gabor filter: What is it for?
Gabor filters, which are well known in the realm of time series analyses, can also be used in HALCON for 2D image analysis. They are particularly useful for detecting textures, patterns, and orientations in complex images.
Read more
Developers Corner
Introduction to new sub-pixel feature of bar code reader
Do you have small resolution bar codes to read but don't get any good results? Then please try our new feature – the subpixel bar code reader.
Read more
Developers Corner
Introduction to XYZ-Mappings (part 2)
This technical article continues our introduction to XYZ-mappings. In the last article, we answered the question "What are XYZ-mappings?" and gave a short preview towards "Why is using XYZ-mappings beneficial for many 3D applications?". Today, we wil…
Read more
Developers Corner
Introduction to XYZ-Mappings (part 1)
This technical article explores the benefits of XYZ-mappings in HALCON, showing how they increase speed, flexibility, and ease of use for many 3D applications.
Read more
Developers Corner
Deep learning: Why is the dataset key for a success result?
Deep learning success starts with the dataset: Learn why acquiring high-quality, well-labeled training data is crucial for reliable classification, detection, segmentation, and anomaly detection in your machine vision applications.
Read more
Developers Corner
How to prepare 3D height images for further processing with MERLIC’s standard tools
Learn how to prepare 3D height images in MERLIC for further processing: convert non-byte images to byte images to enable alignment, embossed text reading, and defect detection with standard easyTouch tools.
Read more
Developers Corner
Deflectrometry demo HALCON
Inspection of specular surfaces with deflectometry in HALCON
Inspect flat and curved reflective surfaces quickly and reliably with HALCON deflectometry: detect scratches, dents, and other defects with synchronized image acquisition and flexible image processing.
Read more
Developers Corner
Deep Learning classifier HALCON
Training a deep learning classifier with HALCON on the embedded board Jetson TX2
Learn how to train a deep learning classifier with HALCON on both a PC and an embedded Jetson TX2 board, from image acquisition to model training and inference, for efficient machine vision applications.
Read more
Developers Corner
Add touch input to the HSmartWindowControlWPF
Learn how to easily add touch input, including pinch-to-zoom, to the HSmartWindowControlWPF in HALCON, leveraging WPF’s built-in multi-touch events for intuitive image control.
Read more
Developers Corner
Increasing Speed in Deflectometry Set-ups
Discover three approaches to increase speed in deflectometry setups, from simple software-based synchronization to hardware triggers and FPGA-based real-time control, enabling faster and more precise inspection of reflective surfaces.
Read more
Developers Corner
HDevelop matching assistant speedup greediness
Speeding up shape-based matching with "Greediness"
Learn how the 'Greediness' parameter in shape-based matching balances speed and detection completeness, enabling faster searches while maintaining robust results in HALCON.
Read more
Developers Corner
Best practice for classification and OCR
Discover best practices for setting up classification and OCR in HALCON using the HDevelop OCR Training File Browser – quickly review, correct, and optimize your training data to improve segmentation and classification results.
Read more
Developers Corner
Rejection all classes 1.5
How to use rejection classes in MVTec HALCON
Learn how to handle outlier samples in MVTec HALCON by using rejection classes in MLP classifiers – automatically generate samples outside the training classes to improve classification reliability.
Read more
Developers Corner
MVTec Software