HALCON – Industrial Image Processing & Machine Vision

With our Ezpire module for HALCON we bring MVTec's leading standard software for industrial image processing to your PHYTEC Vision System. Whether you want to implement sophisticated deep learning algorithms, precise metrology, or classic defect detection – our Vision BSPs offer the ideal foundation. Test the performance for free using the integrated HPEEK demo tool, or use your existing full HALCON licenses for direct, low-level access to our phyCAM modules.

What are HALCON and HPEEK?

MVTec HALCON is the comprehensive standard software for machine vision with an integrated development environment (HDevelop). It is used worldwide in factory automation, robotics, and quality control.

HPEEK is the corresponding, royalty-free embedded evaluation software from MVTec. It allows you to test HALCON's performance on embedded devices – like our NXP i.MX phyBOARDs – in advance.

In the PHYTEC context, we ensure that HALCON communicates seamlessly with the underlying Linux architecture and the V4L2 interfaces of our cameras, allowing you to execute your HDevelop scripts directly on our boards.

What We Deliver: HALCON Out of the Box

Setting up comprehensive software suites on embedded systems can be time-consuming. We simplify this process for you:

  • Pre-built FTP Images: In addition to our standard Vision BSP, we offer specially pre-compiled SD card images on our FTP server where HALCON/HPEEK and the PHYTEC demos are already pre-installed.

  • Two-Way Evaluation: Use HPEEK completely license-free for initial performance tests, or plug in your HALCON license dongle to access live video streams from the phyCAM modules.

  • Hardware Routing Made Easy: We provide startup scripts that handle the complex connection setup between the camera sensor and HALCON – either as a direct stream or pre-processed through a hardware ISP.

  • Display Integration: Our scripts are optimized for the Weston/Wayland display server, ensuring that screen outputs and HALCON GUIs are rendered directly and smoothly on connected monitors (e.g., via HDMI).

Technical Deep Dive

Memory Management and System Architecture
Due to HALCON's extensive feature set and associated deep learning models, the system requires sufficient storage space. When installing manually via our standard BSPs, the SD card's file system partition must be manually expanded to the full card size after flashing (e.g., using the parted tool). Our specially prepared FTP images take care of this step for you out of the box.

Display and User Management (Wayland/Weston)
For graphical output of HALCON scripts, modern NXP processors use the Wayland display manager via the weston user. Newer Linux versions can occasionally experience permission issues here. To prevent this, our setup scripts automatically configure the HALCON directory for the Weston user if needed. Scripts are executed in the correct user environment with the display environment variable set (DISPLAY=:0.0), guaranteeing zero-latency image output on the monitor.

Sensor Routing: ISI vs. ISP
As soon as a full HALCON license (with dongle) is used, the software can access the live data stream of the phyCAM camera modules. We offer different routing paths that are loaded in the boot environment depending on the SoC's capabilities. Before HALCON can access the image stream, the camera and the processor's camera interface are configured using the media-ctl tool. Fetching and forwarding the image data from the video device is conveniently configured via a GStreamer pipeline within HALCON:

  • Direct path (ISI - Image Sensor Interface): Here, HALCON retrieves the data at the end of the GStreamer pipeline. This path is particularly suitable for receiving and processing data in its most "raw" form.

  • ISP Path: For processors with an integrated Image Signal Processor (like the i.MX 8M Plus), startup scripts route the data stream through the hardware ISP first. HALCON then also retrieves the data via a GStreamer pipeline. However, it receives an already optimally color-corrected and debayered image, massively offloading the CPU and freeing up valuable compute time for the actual machine vision algorithms.

Recommended Hardware

To evaluate our System on Modules and phyCAM modules in practice, we offer tailored Embedded Vision Development Kits These bundles contain everything you need to get started: a System on Module (SoM), baseboard, camera, lens, and a downloadable, pre-installed Vision BSP including HPEEK and the HALCON examples.

For demanding video applications, we particularly recommend these platforms:

Our reference platform for embedded vision — featuring a dual ISP and a dedicated AI accelerator (NPU) for high-performance multi-camera setups.

The next generation of architecture, equipped with massive AI compute power and the latest MIPI-CSI interfaces for high-resolution streaming.

You can find additional vision setups for other SoCs and form factors on our Imaging Kit Overview Page.

The PHYTEC phyCAM Portfolio
The HALCON integration unlocks its full potential when paired with our extensive range of industrial-grade camera modules (phyCAM series).Whether you need a rolling shutter or global shutter, monochrome or color, from 1 megapixel up to 4K resolutions — our hardware and software drivers are perfectly matched.

Which setup best suits your requirements? Thanks to the standardized phyCAM interface, camera modules can be easily interchanged. Reach out to us – we are happy to help you select the right hardware.

Links & Resources

Due to MVTec's licensing structure, getting started with HALCON is slightly different than with pure open-source tools. You have two options:

1. The Fastest Way: Pre-compiled FTP Images
For selected kits (like the phyBOARD-Pollux), we offer ready-made SD card images on our FTP server where the Vision BSP and HPEEK/HALCON are completely pre-installed. Flash this image, boot the system, and start the HPEEK demo right away. To test the HALCON demos with live camera data, you will need an MVTec license dongle.

2. Manual Installation via the Standard Vision BSP
If you are using our regular phytec-vision-image:

  1. Flash the image to a microSD card (min. 4GB) and expand the partition size after the first boot.

  2. Register on the MVTec website for Embedded Vision and download the Linux ARM (64-bit) version of HPEEK/HALCON.

  3. Copy the archive to your board, extract it, and adjust the permissions for the display user.

HPEEK Demos vs. Live Camera Access

  • HPEEK Demos: Can be launched immediately and without a license via the command line (e.g., for deep learning evaluations).

  • Live phyCAM Access: As soon as you want to run custom HDevelop demos with real camera feeds, a valid HALCON license is required. Copy your license file to the board and plug in the MVTec dongle. Our provided startup scripts will then initialize the data path between the camera and HALCON.