VISION 2024 (Oct 8-10)
Offical launch of NATvision solutions at booth 10H46 in hall 10 - Free tickets available
Bonn/Germany, October 2024 - At VISION 2024, N.A.T. launches its hybrid and modular NATvision platform where we combine the best of FPGA (Field Programmable Gate Array) and CPU ( X86 / ARM) for real-time imaging data analytics and processing.
Please join us in hall 10 at booth 10H46 and experience our life demos covering real-time Vision examples as well as an AI supported object detection and -tracking system to get detailed information about our latest products around the NATvision platform.
Your free exhibition ticket is available here:
Simply use the promotion code 10H46NATvision and get your free ticket.
NATvision is modular
NATvision is built on AMD ZYNQ Ultrascale+ MPSocs for faster and energy-efficient preprocessing and different FMC Modules to support the required camera interfaces. Depending on the customer's needs, the MPSoCs are available in different variants. IEEE1588 for high-precision time synchronization of all connected cameras is supported naturally.
The in-house GigEVision camera-stack for the FPGA cards is modular as well, so the platform can be adapted to individual tasks and transmission speeds.
Moreover, NATvision can be supplemented with additional processors and AI accelerators from NAT and other Vendors who support the open industrial standards from PICMG and VITA around AMC/MTCA and FMC/FMC+ specification.
NATvision is scalable
Up to 12 FPGA cards can be combined in one MTCA system, so enormous amounts of data can be transferred flexibly between these modules via the highspeed backplane. The system is suitable for connections with a data throughput of up to 100 GbE per camera.
Wide range of applications
As NATvision enables the use of high-resolution, high-end cameras for inspection, quality control, and monitoring, the system aims at the entire value chain of industrial companies - from development and production to packaging. Applications may be analyzing off-rollable meterage, printed items, and bulk materials as well as semiconductors and electronic assemblies.
Another field of application is aerospace and automotive testing e.g., material stress tests, crash tests, airbag dynamics, aerodynamics, combustion processes in engines, or thermal measurement.
NATvision is also suited for safety and security applications like accident prevention in intelligent transport systems (e.g. railway technology), medical imaging (e.g. X-ray), and science/research (physics, chemistry, and biology/biomechanics).
Live demo
The performance of the new real-time FPGA-based NATvision platform in high-speed/high-res vision applications will be demonstrated using a live demo that captures and visualizes the trajectory of a ball in real time.
NATvision enables calculated trajectory predictions to be made, on the basis of which corresponding trigger and output signals can be initiated. Motion control systems can use such calculations to precisely identify goods that are recognized as faulty e.g., to exclude them from the further production process at the appropriate point using a generated trigger.
As part of the live demo, the image data is recorded with a 4K Ultra HD GigEVision camera with a resolution of 3,840 x 2,160 pixels at a frame rate of up to 180 frames/sec. Digital video data streams of up to 35 Gbit/s per camera stream are transmitted and processed in the FPGA using N.A.T.'s own GigEVision firmware package. These data are then available for further FPGA-based processing as an AXI stream. Finally, the video data is written to the RAM of the FPGA-integrated ARM cores – which support Linux – via DMA. From there, data can be transferred to other boards @ 64/128 GTPS or external nodes with up to 2 x 100 GbE via the system uplinks. GPUs and AI accelerators can also be integrated as additional cards.
Currently, each FPGA card can receive and process up to 40Gb/s of image data per camera. This value will increase to 100Gb/s in future. The measured processing latency in the FPGA for the complete preprocessing is less than 500ns, while the processing speed is deterministic in every configuration.
Components of the NATvision platform:
- NATIVEserver, an embedded NATvision system with integrated CPU, eMCH, PM, and up to 4 FPGA card slots
- NAT-AMC-ZYNQUP-ECO with Xilinx ZynqUP ZU2 – ZU5 MPSoC
- NAT-AMC-ZYNQUP-ADV with Xilinx ZynqUP ZU7 – ZU11
- NAT-FMC-PoE and NAT-FMC-HDMI
- NAT-FMC-SFP
- A NATvision Board Support Package (BSP) including GigEVision stack, GenICam, and sample applications for development teams