FantoVision40-CXP12
Mini Edge AI System with:
Built-in Quad CXP-12 Frame Grabber
The FantoVision40 Family delivers compact NVIDIA Jetson systems with built-in FPGA frame grabbers, combining high-bandwidth camera acquisition with deterministic, low-latency FPGA processing. Supporting up to four CXP-12 links with optional connectivity for up to four 10 GigE Vision cameras, these systems reduce processing overhead on Jetson and preserve resources for CUDA-based imaging and AI.
| Product Name | FantoVision40-CXP12 | FantoVision40 |
|---|---|---|
| Product Image |
|
|
| Jetson Model | Orin NX 16GB | Orin NX 16GB |
| Camera Input Options |
|
|
| Camera Input Connectors | 4 × Micro-BNC |
|
| Aggregate Bandwidth | Up to 50 Gb/s | Up to 50 Gb/s |
| Real-Time ROI Offload | ✓ | ✓ |
| Real-Time Encoders | ||
| Real-Time FPGA Image Processing |
|
|
| Dimensions (L/W/H) | 134 × 90 × 60 mm | 134 × 90 × 60 mm |
| Weight | 750 g | 750 g |
| Cooling Options |
|
|
| Storage | Up to 8TB | Up to 8TB |
In each FantoVision40 system, the built-in Altera FPGA frame grabber manages high-speed camera acquisition and can perform inline real-time processing, including Compression, HDR, Detection, and image enhancements, before data reaches NVIDIA Jetson. This reduces processing overhead on Jetson and preserves resources for CUDA-based imaging and AI.
Need more information?
Join Reuven Weintraub, founder and CTO of Gidel, as he reveals how to unlock exceptional image processing performance by adding FPGA’s processing to NVIDIA Jetson edge AI systems.
Reuven Weintraub – Gidel Founder and CTO describes how to boost performance in Machine Vision and Imaging systems. This talk has been given at the Vision Show 2024 Stuttgart, during the Vision Days Forum.
Gidel FantoVision40 edge AI and frame grabber systems at the Embedded World show 2024.
A short video introduction of the FantoVision edge AI frame grabber systems – 2023.
Gidel presented its FPGA-based architecture capable of processing Giga+ Pixels per second while maintaining exceptionally low power consumption.
The session demonstrated how Gidel’s scalable FPGA solutions deliver real-time imaging performance, energy efficiency, and deterministic throughput for advanced vision and imaging systems.
Reuven Weintraub, Founder and CTO of Gidel, presented Gidel’s solutions to perform high-bandwidth imaging on the edge at InVision TechTalk webinar held on September 2023.
Gidel founder and CTO Reuven Weintraub present the new FantoVision edge computers for CoaXPress and 10 GigE Vision interface for embedded vision on the edge at the Embedded World Show 2022 in Nuremberg, Germany.
Presented by Reuven Weintraub, this talk highlighted Gidel’s expertise in real-time processing over Gigapixel/s image streams, demonstrating how FPGA-based architectures enable deterministic latency, scalable throughput, and efficient handling of ultra–high-resolution vision data.
Ron Muller presenting Gidel’s first heterogeneous Edge AI System combining FPGA and NVIDIA Jetson at Industrial Vision Days conference at VISION 2021 show in Stuttgart, Germany.
The correct FantoVision40 system depends primarily on the required camera interfaces. The FantoVision40-CXP12 provides dedicated high-speed CoaXPress-12 acquisition with up to 4 × CXP-12 links and PoCXP. The dual-interface FantoVision40 combines CoaXPress-12 with optional 10 GigE Vision acquisition in a single NVIDIA Jetson + FPGA system for applications requiring both camera interfaces.
Yes. FantoVision40 systems use an integrated Altera Arria 10 FPGA to perform selected image processing directly in the acquisition flow before the data reaches the NVIDIA Jetson module. Available options include real-time Compression, HDR correction, Detection, image enhancement, and custom FPGA processing, helping reduce bandwidth, storage requirements, and Jetson processing load.
Yes. By utilizing Gidel’s InfiniVision™ architecture, FantoVision40 systems can support deterministic, synchronized acquisition from 100+ CoaXPress and GigE Vision cameras across scalable multi-system configurations. The FPGA-based acquisition layer provides precise synchronization and deterministic data handling for demanding multi-camera, high-speed, and high-resolution vision applications.
FantoVision40 family provides a dual-development environment. NVIDIA CUDA, C/C++, and AI libraries can be used for GPU and application development on Jetson, while Gidel’s ProcVision™ Suite supports FPGA acquisition, preprocessing, and custom image-processing development. This allows processing to be split or chained between the FPGA and Jetson according to application requirements.
A Gidel FantoVision40 system is a complete embedded vision platform that combines CoaXPress and optional GigE Vision acquisition, an NVIDIA Jetson processor, and optional real-time FPGA image processing in one compact Edge AI system. A PCIe CoaXPress or GigE Vision frame grabber is an acquisition card installed in a host computer and transfers image data through PCIe for processing by the host system. The correct platform depends on whether the application requires a complete embedded Jetson + FPGA vision system or a host-based PCIe acquisition card.
Our experts can help you find the right product for your specific requirements.
Or contact us directly:
[email protected]