内页banner

Gidel

Position:Home > PRODUCTS > Edge Computers > Gidel
FantoVision40-CXP12: Mini Jetson CoaXPress Frame Grabber & Edge AI System

FantoVision40-CXP12: Mini Jetson CoaXPress Frame Grabber & Edge AI System

  • Category:Gidel
  • Visits: 118 Clicked
  • Date:2026-07-03 17:11:37
  • Download:
  • Details

Integrated Quad CXP-12 Interface with NVIDIA Jetson

1. High-speed FPGA-based Edge AI system: up to 50 Gb/s

2. Integrated Quad CoaXPress, CXP-12 frame grabber links with PoCXP

3. NVIDIA Jetson Orin | Xavier NX SoM

4. Altera Arria 10 FPGA for image acquisition and pre-processing

5. Direct transfer of image buffers from FPGA to GPU memory

6. Dimensions: 134 x 90 x 60 mm | Weight: 750 g

7. Inline FPGA image processing options include:

    · Real-time detection for object, event, or feature identification

    · On-FPGA real-time compression: JPEG, Lossless, Quality+

    · Real-time High Dynamic Range (HDR) correction

8. Jetson processing options:

    · Compression: H.264 | H.265

    · RTSP output option

 

DESCRIPTION

 

Jetson with Quad CoaXPress-12 Frame Grabber

The FantoVision40-CXP12 is a rugged Jetson system with a fully integrated CoaXPress-12 frame grabber. Powered by the NVIDIA Jetson Orin NX, it captures and processes up to 4 × CoaXPress CXP-12 links with PoCXP. It merges high-end image acquisition on an Arria 10™ FPGA with real-time GPU processing on Jetson, enabling low-latency recording, streaming, and Edge AI in an ultra-compact, Low SWaP form factor.

 

Jetson CXP-12 Acquisition with Real-Time FPGA Image Processing

The FantoVision40-CXP12 is available as a plug-and-play CoaXPress frame grabber system or as part of a complete Imaging & Vision solution with real-time FPGA preprocessing, image enhancement, and compression options.

The built-in FPGA can process image data during acquisition, before it reaches the Jetson module. This helps reduce bandwidth, storage, and Jetson processing load while preserving low-latency performance for high-speed camera streams.

Optional FPGA processing includes Compression, HDR correction, Detection, and additional image enhancement modules.

Real-Time FPGA Processing Helps Enable:

Reduced bandwidth for high-throughput image acquisition

Low-latency processing directly in the acquisition flow

Extended recording time through real-time compression

Lower Jetson processing load by offloading selected tasks to the FPGA

Custom image pipelines using Gidel IPs or user FPGA logic

For the full list of available image processing and enhancement options, please refer to the Options tab.

 

Flexible Development Tools

· Open architecture: split/chain processing between FPGA and GPU

· GPU development: CUDA | C/C++ and NVIDIA AI libraries on Jetson

· FPGA development: rapid pre-processing deployment with ProcVision Suite

 

Integrated Vision Acquisition and Processing

Deploy a single compact node for acquisition, real-time pre-processing, Edge AI inference, and recording. This approach reduces cabling, latency, and overall system cost while improving reliability and maintainability.

For large-scale, synchronized camera deployments, Gidel’s InfiniVision multi-camera vision system enables synchronization and processing across 100+ sensors within a flexible acquisition framework.

For applications that require strict determinism, line-scan optimization, or guaranteed frame capture with fixed timing, ProcFG provides a dedicated deterministic image acquisition layer.

Both approaches integrate seamlessly into Gidel’s FPGA-based vision platforms and scale from single-node systems to multi-unit topologies.

 

Why Choose the FantoVision40-CXP12?

· Compact NVIDIA Jetson system with built-in Quad CXP-12 FPGA frame grabber

· PoCXP support for long-reach, robust camera connectivity

· Up to 50 Gb/s aggregate input bandwidth

· FPGA-plus-GPU architecture for low-latency acquisition, processing, recording, streaming, & Edge AI

· Optional real-time FPGA processing, image enhancement and compression IPs

The FantoVision40-CXP12 is the ideal choice when you need maximum CoaXPress throughput in a compact, low-latency Jetson platform.

 

SPECIFICATIONS


General

Supported Protocols

CoaXPress 2.1

Camera Input Options

· 4 x CoaXPress-12 links

· 2 x CoaXPress-12 links

· 1 x CoaXPress-12 link

· PoCXP

Camera Input Connectors

4 x Micro-BNC

Supported CXP Downlink Speeds

· 1.25 Gb/s | CXP-1

· 2.5 Gb/s | CXP-2

· 3.125 Gb/s | CXP-3

· 5 Gb/s | CXP-5

· 6.25 Gb/s | CXP-6

· 10 Gb/s | CXP-10

· 12.5 Gb/s | CXP-12

Supported CXP Uplink Speeds

· 20.83 Mbps (CXP-1 to CXP-6)

· 41.66 Mbps (CXP-10, CXP-12)

Maximum Stream Packet Size

8,192 bytes

Advanced Features

· On-the -fly selective ROI acquisition

· Link Aggregation mode

· Chunk Data

Jetson Host Interfaces

· 1 x GbE

· 1 x USB 3.2 Gen 2 (single lane)

· 1 x USB 2.0

· 1 x HDMI Out

· 1 x Recovery

· 1 x Restart

· 1 x UART

Max USB 3.x power allocation: ≤ 4 W

Storage

NVMe interface:Gen 4 ×2

· Up to 8TB

Image Formats

· Mono, Bayer, RGBA (8, 10, 12, 14 and 16 bits/color)

· RGB (8, 10 and 12 bits/color)

Max. Resolution

· Horizontal: 16 K pixels (64-bit)

· Vertical: 65 K lines

· For configurations supporting higher resolutions- Contact Us

Real-Time Image Compression

Supports optional FPGA-based and Jetson-based compression options.
For the full list, please refer to the Options tab.

Real-Time FPGA Image Processing & Enhancements

Supports optional FPGA image processing and enhancement modules.

For the full list, please refer to the Options tab.

Maximum Acquisition Throughput

40 Gb/s

Camera Types

· Area

· Line Scan

GPIO

· 8 x RS422 deferential pairs

· 4 x Opto-Isolators

· 6 x High-Drive output

(including COMMON for discharge loop)

· 4 x LVTTL

· GPIO power out: 2 x 12V @ 1.0A aggregate

· CAN bus

Streaming & Communication Protocols

· Customizable streaming & communication using NVIDIA tools

· RTSP streaming option

Dimensions

134L x 90W x 60H mm

Weight

750g

Cooling

· Passive cooling

· Active cooling (Fan)

MTBF

MTBF values at 60% confidence and 40 °C case temperature are:
>650Kh (With Passive Cooling)

Certifications

· CE

· FCC

· CCI

Processors

Embedded computer

NVIDIA Jetson Orin NX 16GB

Jetson computer resources

JNVIDIA Jetson Orin NX 16GB:

· JetPack 6.2.1

· Up to 8-core Arm Cortex-A78AE 2MB L2 + 4MB L3

· 1024 Core Ampere, with 32 Tensor Cores

· Up to 157 TOPS AI computation

· Up to 16GB @ 102.4 GB/s

· Video encode: 1 x 4K60, 3 x 4K30, 6 x 1080p60, 12 x 1080p30 (H.265), H.264, H.265, AV1

· Video decode: 1 x 8K30,2 x 4K60, 4 x 4K30, 9 x 1080p60, 18 x 1080p30 (H.265), H.264, H.265, VP9, AV1

FPGA Types

Altera Arria 10:

· 160 GX

· 270 GX

· 660 GX

GPU-FPGA interconnectivity

PCIe Gen 3 x4 @ up to 26.4 Gb/s

Environmental Conditions

Temperature Range

· Commercial: 0 °C - 65 °C case temperature

· Industrial: -25 °C - 65 °C case temperature. (Limited FPGA options)

IP Compliance

· IP51-compliant

· For configurations meeting higher IP standards, contact us

Environmental Compliance

· RoHS

· Conflict Minerals

· ISO

· Reach

 

 

 


Mark

Contact

Service Hotline

18901088856

Website:http://en.cnimage.com/

Email:vision2010@cnimage.com

Address:Rm1-1705, Guoji Keji Chuangye Garden, No.1 Shangdi Xinxi Road, Haidian District,100085,Beijing PRC