Halcon compatible with MIPI

Share this on social media:

HALCON, the standard machine vision software from MVTec Software GmbH (www.mvtec.com), is well prepared for new developments in the embedded vision environment. The leading provider of modern machine vision software offers proof that its software can acquire and process images from MIPI (Mobile Industry Processor Interface) camera modules. Existing HALCON interfaces, such as Video4Linux, GenTL, as well as shared memory access, can be used for this. The hardware interface experts at MVTec have successfully tested the VC MIPI OV 9281 camera module from Vision Components in conjunction with Raspberry Pi 3 and 4, using HALCON 19.05. They also utilized the same HALCON version to successfully test the MIPI IMX290 sensor module from The Imaging Source on an NVIDIA Jetson Nano via FPD-Link III (cable lengths of up to 15 meters). These tests document for the first time that the machine vision software is fully compatible with the camera modules, which were developed specifically for high-volume embedded applications and that meet strict industrial standards.

Prominent hardware manufacturers, such as NVIDIA, NXP, and the Raspberry Pi Foundation, already provide dedicated interfaces for MIPI as a standard feature. The transmission standard allows for the seamless integration of a wide range of image sensors. Thus, digital image data can be acquired – to some extent – without imposing any additional load on the CPUs of embedded devices. This makes it possible to use the full performance of the processors for vision applications. Users also benefit from a maximum transmission rate of up to 17.1 Gbit/s. With these advantages, MIPI paves the way for entirely new business areas beyond industrial machine vision, thanks in part to the lower cost of embedded devices. Such areas include medical technology, agriculture, as well as the logistics and retail sectors. New applications are now possible, which could not previously be implemented with embedded devices due to unsuitable sensor modules.

HALCON features for all industries

With this hardware configuration, MVTec will also support all HALCON core technologies like matching, identification, or measuring, as well as the latest features, such as an executable deep learning inference on Arm® CPUs. This will benefit all industries.

In addition, the company plans to conduct joint demonstrations with Vision Components and The Imaging Source at Embedded VISION Europe on October 24 and 25 in Stuttgart, Germany.

"MIPI has the potential to revolutionize the embedded vision environment. As the technology leader in machine vision, we are at the forefront of these developments. The technology also enables us to gain a foothold in other embedded vision areas. Our performance verification tests demonstrate that HALCON is ready for MIPI-based solutions. This can also be transferred to other combinations of customary MIPI camera modules and platforms," explains Christoph Wagner, Embedded Vision Product Manager at MVTec.

Stephen Su shares how Arm’s Cortex-M85 processor and software ecosystem can be leveraged to overcome the constraints of microcontroller unit platforms

16 March 2023

Advances in the technology suggest this may be a tipping point, says Rafael Romay-Juarez at this year's EMVA Business Conference

05 May 2023

Image: Sergey Nivens/shutterstock.com

12 April 2023

Stephen Su shares how Arm’s Cortex-M85 processor and software ecosystem can be leveraged to overcome the constraints of microcontroller unit platforms

16 March 2023

The FSM-IMX570 Devkit provides a simple, coherent framework for quickly developing a working prototype of an indirect time-of-flight embedded vision system

15 March 2023