It also integrates seamlessly with Basler's embedded vision software to provide OEMs with a ready-to-use solution platform for developing next-generation, AI-accelerated embedded vision systems. Typical applications are diverse, ranging from price-sensitive automated checkout terminals in retail to building security, and from in-vehicle vision for navigation to surveillance systems in buses. Industrial use cases include HMIs with vision-based user identification and gesture-based machine operation, as well as vision-assisted robotics and industrial quality inspection systems.
 
"A dedicated processing unit for neural algorithms, supported by open-source AI software solutions like TensorFlow, is an efficiency accelerator for many vision-based systems. And when all of this is integrated as an application-ready platform, validated by both hardware and software, including the Basler Pylon Camera Software Suite, it puts developers on a fast track to designing NPU-accelerated intelligent vision applications," explains Martin Danzer, Director of Product Management at congatec.
 
The Basler pylon Camera Software Suite offers a unified SDK for BCON for MIPI, USB3, and GigE vision cameras, enabling camera access from source code, GUI, or third-party software. The high-performance pylon viewer is ideal for camera evaluation. Thanks to its integration into the congatec i.MX 8M Plus Starter Kit for AI-accelerated vision applications, engineers gain instant access to key AI-supported machine vision features such as triggering, single image capture, and highly differentiated camera configuration options, as well as easy access to custom inference algorithms based on the Arm NN and TensorFlow Lite ecosystem.
 
The feature set in detail:
The new AI-accelerated vision application starter kit contains the entire ecosystem developers need to instantly begin designing applications on this next-generation platform, which offers highly efficient vision and AI integration. At the heart of the kit is the new conga-SMX8-Plus COM SMARC 2.1 module. It features four powerful Arm Cortex-A53 cores, one Arm Cortex-M72 controller, and an NXP NPU to accelerate deep learning algorithms, and comes with passive cooling. The 3.5-inch conga-SMC1/SMARC-ARM motherboard directly connects the Basler dart daA4200-30mci BCON for MIPI 13MP camera with an F1.8 f4mm lens via MIPI CSI-2.0 without the need for additional converter modules. In addition to MIPI CSI-2.0, USB and GigE vision cameras are also supported. Regarding software, congatec provides a bootable SD card with a pre-configured bootloader, a Yocto operating system image, the corresponding BSPs, and processor-optimized Basler embedded vision software that enables immediate AI inference training from captured images and video footage.

More information or a quote