FantoVision 20 Edge Computer

Edge computer with 10GigE and Camera Link interface

Video, Machine Vision and AI Inferences on the Edge
Gidel’s FantoVision 20™ is a pioneering compact computer enabling image acquisition and processing from 2 x 10 GigE Vision and from 80- bit or Dual-Base Camera Link cameras. The FantoVision’s innovative architecture merges high-end image acquisition with real-time image processing and/or compression using Nvidia Jetson™ embedded computer with optional pre-processing/compression on Intel Arria 10™ FPGA. The Jetson boasts up to 21 TOPS AI compute capability using Nvidia’s comprehensive libraries. The GPU and FPGA interconnect via 4-lane PCIe capable of up to 20 Gb/s. With up to Tera Byte+ SSD, the system can perform demanding real-time processing, compression, and recording. The FPGA is fortified with up to 10 GB DDR4 @ 200 Gb/s.

Open Customizable Image Processing
The FantoVision is also distinct in its open architecture enabling embedded AI/image processing on GPU and FPGA. Software engineers can program their algorithms on GPU using CUDA C/C++ and NVIDIA’s AI libraries. In addition, developing and deploying optional preprocessing block on FPGA is simple and fast using Gidel’s novel ProcVision™ Suite.

Scalable Solution
The FantoVision opens the way for new compact, cost-effective, scalable vision and imaging solutions for high-bandwidth, low-latency applications. Multi-FantoVision units can be interconnected to provide unique and scalable topologies. Using Gidel’s InfiniVision™ open frame grabber flow, 100+ sensors can be synchronized and processed simultaneously.

Interfaces:
Camera interfaces
2 x 10GigE-Vision
Camera Link (up to 80-bit/Dual-Base)
Host interfaces
1x GigE
1x USB 3.1/2.0
1x HDMI
UART
Recovery
Restart
Processors:
Embedded computer
NVIDIA Jetson Orin and Xavier NX
(For availability of Orin NX, contact Gidel)
Jetson computer resources
Up to 6-core Nvidia ARM CPU
GPU: up to 384 cores + 48 Tensor Cores (Nvidia Volta)
Up to 21 TOPS AI computation
Up to 8 GB LPDDR4 @ 51.2 GB/s
H.264/5, VP9 encoding/decoding
FPGA
Intel Arria 10 – 160/270/660
FPGA resources
160K/270K/660K LEs
2GB – 10GB DDR4 @ up to 25.6 GB/s
Up to 2,133 M20Ks
Up to 3,374 18 x 19 multipliers
Up to 16 I/O PLLs
GPU-FPGA interconnectivity
PCIe Gen 3 x4 @ up to 20 Gb/s

Options
FantoVision 20 is available with active or passive cooling.
Additional customization is available upon request – e.g. different Jetson Processor or frame grabber FPGA.
Contact us for more information!

 

Contact us

Options:
FPGA
Arria 10 160 GX | Arria 10 270 GX | Arria 10 660 GX
Embedded Computer
Jetson Xavier NX | Jetson Orin NX
For availability of Orin NX, contact Gidel.
Cooling
Passive cooling | Active cooling (fan)
On-FPGA Image Compression
Quality+| Lossless | JPG

AI/Algorithm Development

The FantoVision 20 edge computer is supported by NVIDIA’s libraries enabling to develop algorithms/AI on the Jetson via CUDA C/C++.

ProcVision Developer’s Suite

The ProcVision Developer’s Suite provides a powerful set of tools for customizing the frame grabber acquisition path and for developing, testing and verifying the on-FPGA image processing block. The tools include means for developing both the image processing FPGA code and the software application driver. The ProcVision Suite includes:

  • CertifEye Toolchain: Enables instant debugging and validation of the FPGA image processing IP(s) and the ISP pipeline
  • InfiniVision: Frame grabber flow for multi cameras/sensors enabling real-time compression and synchronization of 100+ cameras
  • CamSim: Camera simulator for developing and testing imaging and vision applications
  • Proc Dev Kit: Allows you to fully tailor your grabber’s Application Support Package (ASP) including integration with software
  • Utilities: Load new designs, scan FPGAs, etc.

PDF file
FantoVision20 Datasheet

PDF file - 1.9 MB

Download
Video: Image processing acceleration on NVIDIA Jetson embedded computer

Demo at the Embedded World 2024 show

Watch
Video: Gidel frame grabbers and edge computers

Presentation at the Embedded World show 2024

Watch
TechTalk Embedded Vision webinar: Overcoming bandwidth limitations when imaging on the edge
Video: Overcoming bandwidth limitations when imaging on the edge

InVision TechTalk webinar held on Sept. 19, 2023

Watch
Video: FantoVision edge computers for GigE Vision, CoaXPress and Camera Link applications
FantoVision video clip

A short video introduction to FantoVision edge computers

Watch
Video: FantoVision presentation at Embedded World show 2022
FantoVision at Embedded World 2022

Gidel founder and CTO introduces the FantoVision models

Watch

Need more?
Check out our other products and solutions!

Contact us!