SAN DIEGO – Congatec GmbH in San Diego is introducing a starter set for artificial intelligence accelerated intelligent embedded vision applications ranging from in-vehicle vision for navigation to surveillance systems.
Part of the company's i.MX 8 ecosystem, the kit is based on a Smart Mobility ARChitecture (SMARC) computer-on-module with i.MX 8M Plus processor, the starter set's sweet spot is the utilization of the new processor integrated NXP Neural Processing Unit (NPU).
Delivering up to 2.3 trillions or tera operations per second (TOPS) of performance for deep learning-based artificial intelligence (AI), it can run inference engines and libraries such as Arm Neural Network (NN) and TensorFlow Lite.
It also integrates with Basler embedded vision software to enable systems designers to develop next-generation AI accelerated embedded vision systems.
Industrial use cases include human-machine interfaces with vision-based user identification and gesture-based machine operation as well as vision-supported robotics and industrial quality inspection systems.
The Basler pylon camera software suite delivers a unified software-development for BCON for MIPI, USB3 vision, and Gigabit Ethernet vision cameras, and enables camera access from source code, GUI, or third-party software.
The pylon viewer is for camera evaluation. Thanks to integration in the Congatec i.MX 8M Plus starter set for AI accelerated vision applications, engineers get access to important AI-supported machine vision features such as triggering, individual image capture, and differentiated camera configuration options plus access to customized inference algorithms on the basis of the Arm NN and TensorFlow Lite ecosystem.
The new starter set for AI accelerated vision applications contains the ecosystem developers need to start designing application, which offers efficient vision and AI integration.
Related: Artificial intelligence and machine learning for unmanned vehicles
At the heart of the set is the SMARC 2.1 computer-on-module conga-SMX8-Plus. It features four Arm Cortex-A53 cores, one Arm Cortex-M72 controller, and the NXP neural processing unit (NPU) to accelerate deep learning algorithms and comes with passive cooling.
Congatec provides a bootable SD memory card with preconfigured boot loader, Yocto OS image, matching board support packages, and processor-optimized Basler embedded vision software to enable AI inference training on the basis of captured images and video sequences.
For more information contact Cognatec online at www.congatec.com.
