Skip to main content

Embedded FPGA Solutions for Embedded Vision

Powerful Embedded FPGA processing for Embedded Vision

Gidel’s embedded FPGA solutions address the growing demand for high-performance, compact, and power-efficient embedded systems. Gidel delivers a broad portfolio of modular embedded FPGA platforms, combining compact hardware building blocks with advanced software tools to support a wide range of embedded vision and computing applications. As a market leader in FPGA architectures and algorithms, Gidel enables both rapid deployment using off-the-shelf solutions and deeper customization for advanced users.

Embedded Vision Applications Enabled by Embedded FPGA

As processors become more powerful and increasingly miniaturized, Embedded Vision systems continue to expand into new application domains. These include industrial automation, automotive systems, drones, robotics, and portable devices. Thanks to advances in Embedded Computing and AI, applications that once required stationary and power-hungry PCs can now operate at the edge, integrated directly into vehicles, mobile platforms, or compact devices.

Real-Time Image Processing IPs

In many embedded vision systems, image quality and bandwidth efficiency are critical. Gidel provides a range of hardware-based Compression IPs optimized for real-time embedded imaging:

Design Constraints in Embedded FPGA Systems

Designers of embedded vision systems face strict constraints that drive system architecture decisions:

  • SWaP (Size, Weight, and Power): Keeping systems compact and battery-friendly.
  • Thermal Efficiency: Managing heat in enclosed spaces.
  • Bandwidth: Handling massive data flows between internal hardware and the cloud.

Gidel Embedded FPGA Platforms

With more than 30 years of expertise in FPGA development and acceleration, Gidel helps system designers overcome these challenges. Gidel’s Embedded FPGA Modules and heterogeneous platforms provide deterministic performance while meeting tight SWaP budgets.

Embedded Vision and AI at the Edge

For edge vision and AI workloads, Gidel also offers Mini Jetson Frame Grabbers that tightly integrate embedded FPGA processing with GPU-based AI acceleration.

Software Tools and Customization

To further simplify development, Gidel provides comprehensive Software Development Tools that streamline FPGA programming, system integration, and performance optimization. Together, these embedded FPGA solutions enable faster development cycles, scalable system designs, and reliable deployment of embedded vision and AI systems at the edge.

Need more information?




    Products & Solutions for Embedded Vision

    At Gidel, we specialize in modular, customizable technology to suit your exact requirements.

    Let us help you find the ideal solution – Contact US.

    Gidel FantoVision20 Edge AI: Jetson Orin dual interface frame Grabber system with Dual 10 GigE Vision and Camera Link FPGA Frame Grabber displayed against a digital network connectivity background with Hand

    FantoVision20 Edge AI with FPGA Frame Grabbers

     FantoVision20 Mini NVIDIA Jetson Frame Grabber Systems: Overview & Comparison

    Features & Bandwidth
    Product Name FantoVision20-GigE FantoVision20-CL FantoVision20
    Product Image FantoVision20-GigE: NVIDIA Jetson + Dual 10GigE Vision FPGA frame grabber- Edge AI Vision displayed against a digital network connectivity background Gidel FantoVision20-CL: NVIDIA Jetson + Camera Link FPGA frame grabber- Edge AI Vision displayed against a digital network connectivity background Gidel FantoVision20: NVIDIA Jetson + Dual 10GigE Vision and Camera Link FPGA frame grabbers- Edge AI Vision displayed against a digital network connectivity background
    Jetson Model
    • Orin NX 16GB
    • Xavier NX 8GB | 16GB
    • Orin NX 16GB
    • Xavier NX 8GB | 16GB
    • Orin NX 16GB
    • Xavier NX 8GB | 16GB
    Camera Input
    • 2× 10GigE cameras
    • 4× 5GigE cameras
    • 8× 2.5GigE cameras
    • 15× 1GigE cameras
    • Camera Link Deca / Full / Medium / Base
    • Dual Base
    • Optional: PoCL
    • 2× 10GigE cameras
    • 4× 5GigE cameras
    • 8× 2.5GigE cameras
    • 15× 1GigE cameras
    • Camera Link Deca / Full / Medium / Base
    • Dual Base
    • Optional: PoCL
    Camera Input Connectors 2× SFP+ | 2× RJ45 (Fiber optic / Copper) 2× SDR26 (mini-Camera Link)
    • 2× SFP+ | 2× RJ45 (Fiber optic / Copper)
    • 2× SDR26 (mini-Camera Link)
    Aggregate Bandwidth Up to 20 Gb/s Up to 6.8 Gb/s Up to 26.8 Gb/s
    Real-Time ROI Offload
    Real-Time Encoders (Optional)
    Real-Time HDR Correction
    Dimensions (L/W/H) 134 × 90 × 60 mm 134 × 90 × 60 mm 134 × 90 × 60 mm
    Weight 750 g 750 g 750 g
    Cooling Options Active | Passive Active | Passive Active | Passive
    Storage Up to 8TB Up to 8TB Up to 8TB

    FPGA-Based Camera Acquisition and Processing for Jetson Edge AI

    In each FantoVision20 system, the built-in
    Altera FPGA frame grabber manages high-speed camera acquisition and can perform inline real-time processing, including CompressionHDR, 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?

    [contact-form-7 id="123" title="Contact form 1"]

    View Products
    Gidel ultra-compact FPGA modules with Arria 10 and Stratix 10N displayed against a digital network connectivity background

    Mini FPGA Modules

    Mini FPGA Modules: Overview & Comparison

    Resources Overview
    Resources FDB16 FDB27 FDB66 Proc10N Proc10M
    FPGA Arria 10 160 GX Arria 10 270 GX Arria 10 660 GX Stratix 10 NX 2100 Stratix 10 MX 2100
    DRAM Throughput 12.8 GB/s 12.8 GB/s or 24 GB/s 16.8 GB/s 300 GB/s 300 GB/s
    On-board DDR4 2 or 4 GB 2 or 10 GB 9 GB Up to 128 GB on carrier board Up to 128 GB on carrier board
    On-FPGA DRAM - - - 8 GB HBM2 8 GB HBM2
    Transceivers 12 (2 Rx only) 12 or 16 (2 Rx only) 12 or 16 (2 Rx only) 72 72
    Transceivers Speed Up to 14.2 Gb/s Up to 14.2 Gb/s Up to 14.2 Gb/s Up to 26 Gb/s Up to 26 Gb/s
    I/Os 12×3.0V, 4×1.2V, 36×1.8V 12 or 42×3.0V, 4×1.2V, 36 or 52×1.8V 12 or 42×3.0V, 4×1.2V, 36 or 52×1.8V Up to 374 I/Os: 26×3.3V, 96×LVDS, 72-bit DDR4 Up to 374 I/Os: 26×3.3V, 96×LVDS, 72-bit DDR4
    Dimensions 49 mm × 54 mm 58 mm × 58 mm 58 mm × 58 mm 97.4 mm × 101 mm 97.4 mm × 101 mm
    Weight 30g 35g 35g 385g 385g
    LEs 160K 270K 660K 2,073K 2,073K
    FPGA SRAM - - - 94.5 Mb @ 90 GB/s 94.5 Mb @ 90 GB/s
    M20K 440 750 2133 6800 6800
    18×19 MAC 312 1660 3374 - 7,920
    INT8/FP16 Tensor MAC - - - 118,800 -

    Need more information?

    [contact-form-7 id="067430d" title="Contact form 1"]

    View Products
    Gidel HawkEye GigE Vision, CoaXPress and Camera Link PCIe Frame Grabbers family displayed against a digital network connectivity background

    Frame Grabbers & Image Processing

    High-Performance PCIe GigE Vision Frame Grabbers: Overview

    Throughput
    Product Name HawkEye-20GigE Proc10A-40GigE Proc1C10M-120GigE Proc1C10N-120GigE
    Product Image Gidel HawkEye-20GigE: Dual 10 GigE Vision frame grabber displayed against a digital network connectivity background Gidel Proc10A-40GigE: Quad 10 GigE Vision frame grabber displayed against a digital network connectivity background Gidel Proc1C10M: 12 x 10 GigE Vision frame grabber displayed against a digital network connectivity background GidelProc1C10N: 12 x 10 GigE Vision frame grabber with AI option and tensor blocks displayed against a digital network connectivity background
    Camera Interface Input
    • 2× 10GigE cameras
    • 4× 5GigE cameras
    • 8× 2.5GigE cameras
    • 20× 1GigE cameras
    • 4× 10GigE cameras
    • 8× 5GigE cameras
    • 16× 2.5GigE cameras
    • 30× 1GigE cameras
    • Up to 12× 10GigE cameras
    • 4× 100GigE cameras Option
    • Up to 12× 10GigE cameras
    • 4× 100GigE cameras Option

    High-Performance PCIe CoaXPress Frame Grabbers: Overview

    Throughput
    Product Name HawkEye-CXP12 Proc10A-CXP Proc1C10N-CXP12
    Product Image Gidel HawkEye-CXP12: Quad CXP12 links frame grabber displayed against a digital network connectivity background Gidel Proc10A-CXP6: Octo CXP6 links frame grabber displayed against a digital network connectivity background Gidel Proc1C10N-CXP12: Octo CXP12 links frame grabber displayed against a digital network connectivity background
    Camera Interface Input
    • 1 / 2 / 4× CXP-12 links (PoCXP)
    • 4 / 8× CXP-6 links (PoCXP)
    • Up to 8× CXP-12 links (PoCXP)

    High-Performance PCIe Camera Link Frame Grabber: Overview

    Throughput
    Product Name HawkEye-CL
    Product Image Gidel HawkEye-CL: Camera Link frame grabber displayed against a digital network connectivity background
    Camera Interface Input
    • 1× 80-bit (Deca), Full, Medium, or Base
    • Dual Base
    • PoCL option

    FPGA-Based Acquisition and Inline Processing

    Gidel PCIe frame grabbers manage high-bandwidth camera acquisition directly on the Altera FPGA, enabling deterministic, low-latency data capture while reducing CPU overhead. Optional inline FPGA processing supports real-time image enhancement, CompressionHDR, and data optimization before host-side processing.

    Need more information?

    [contact-form-7 id="123" title="Contact form 1"]

    View Products
    Gidel FPGA Compute Acceleration Boards displayed against a digital network connectivity background
    A hand holding the ultra-compact FantoVision40 and FantoVision 20 Edge AI Vision systems designed for high-speed acquisition and real-time recording, streaming and processing, displayed against a digital network connectivity background

    Low Latency Recording & Streaming Solutions

    Real-Time Recording and Streaming for High-Performance Vision Systems

    Designed for demanding imaging and vision applications, Gidel’s systems combine reliable camera acquisition, inline FPGA processing, and real-time compression to reduce data bottlenecks while preserving image quality. Their compact and flexible architecture supports high-performance recording and streaming close to the image source.

    Rapid Customization for Powerful and Optimized Recording Solutions

    Each imaging application has unique requirements. Therefore, Gidel provides a broad technology framework that supports high-performance cameras and multi-camera configurations. Moreover, our recording solutions are designed for fast customization. This allows customers to optimize the system for their exact use case without long development cycles. Customization can be done by the customer, or with Gidel expert support. In either case, the process is streamlined and fast. As a result, customers can reach a tailored, production-ready solution more quickly.

    We support a variety of high-performance camera protocols, including:
    1. CoaXPress-12: Supporting cameras with data rates of 40 Gb/s and beyond.
    2. GigE Vision (10 GigE): Offering data rates up to 40 Gb/s and beyond.
    3. Camera Link: Flexible compatibility with this widely used interface.
    4. User-Defined Protocols: Enabling adaptation to proprietary or emerging camera protocols as needed. 
    Typical use cases include defense and aerospace, ISR, drones and UAVs, unmanned and robotic systems, volumetric and medical imaging, smart cities, and sports analytics.

    Need more information?

    [contact-form-7 id="067430d" title="Contact form 1"]

    View Products
    Gidel GIL - FPGA Vision and Imaging libraries (IPs)

    GIL - Gidel Imaging Libraries (IPs)

    CPU Offload with FPGA Imaging Libraries

    Gidel’s FPGA libraries (IPs) offer off-the-shelf, ready-to-integrate solutions that have empowered customers for decades. These IPs help accelerate system performance, implement custom algorithms, and meet compute-intensive requirements. Thanks to Gidel’s innovative development tools, integrating these IPs is fast and seamless—dramatically reducing development time and complexity. One of the most significant advantages is CPU Offloading using FPGA, which enhances system efficiency by moving heavy computation from the CPU to the FPGA. As a result, users benefit from higher processing speeds, lower latency, and reduced power consumption. Moreover, Gidel’s systems support FPGA virtualization, a unique capability enabled by Gidel’s architecture. This allows multiple applications to access and run on the FPGA concurrently, increasing resource utilization and design flexibility. Ultimately, Gidel’s IP libraries help developers build high-performance, reliable
    imaging and vision systems with minimal effort—unlocking the full potential of CPU Offloading using FPGA to overcome today’s most demanding technical challenges.

    GIL (Gidel Imaging Libraries)

    The GIL is High-Performance, Low Latency, Resource optimized FPGA library (set of FPGA IPs) includes:
    • System: Multiport, MultiFIFO, MegaDelay, Total History, etc.
    • Camera Interfaces: 1-120 GigE, CXP-12, Camera Link, User Interface.
    • Image Acquisition: ProcFG, InfiniVision, Custom multiple I/Fs.
    • Image Processing System: Rate control, line delay, etc.
    • Imaging/Vision Acquisition: demosaic, Color ORV, Binning, open/close morphology, histogram, etc.
    • Debug/Testing/Validation: CertifEye, TotalHistory.
    • Compression: JPEG, lossless, Quality+, integration of 3rd party.
    • GenICam: Camera control and streaming.

    View Products
    Gidel Real-Time FPGA Image Compression IPs

    Image Compression IPs

    Compression IPs: Overview

    • JPEG Encoder IP – Real-time JPEG compression on FPGA with ultra-low latency, adjustable compression, and efficient silicon use.

    • Lossless Compression IP – Preserves full image data with zero quality loss, perfect for precision-critical applications.

    • Quality+ compression IP – Patented, training-based algorithm achieving up to 10:1 compression while preserving and enhancing image SNR, ideal for demanding Imaging & Vision applications.

    Gidel’s compression solutions reduce bandwidth, minimize storage, and enhance overall system performance—all in real time.

    View Products
    Gidel FPGA development tools

    Development Tools for Imaging & Vision Applications

    Gidel provides a comprehensive development tool suite for customizing its PCIe Frame Grabbers, Mini Jetson Frame Grabber Systems and Mini FPGA Modules, enabling customers to build tailored, high-performance Imaging & Vision systems.

    For advanced development, ProcWizard and Gidel templates enable real-time on-FPGA processing and system architecture customization, including software, I/O interfaces, and HDL design code. The suite can automatically generate the board’s Application Support Package (ASP), including software drivers, the HDL top-level envelope, interface bridges, and Gidel proprietary IPs such as Compression and HDR.

    Gidel’s MultiPort memory controller can also be seamlessly integrated, enabling simultaneous multi-application access to the frame grabber and supporting flexible, scalable Imaging & Vision development.

    Need more information?

    [contact-form-7 id="067430d" title="Contact form 1"]

    View Products

    Resources

    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.

    Image processing acceleration on NVIDIA Jetson embedded computer at the Embedded World 2024 show.

    Gidel edge computers and frame grabbers at the Embedded World show 2024.

    A short video introduction to FantoVision edge computers – 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 explain the benefits of Gidel’s Altera-based high-performance FPGA modules for fast and easy development.

    Key features of all modules at a glance.

    Gidel founder and CTO Reuven Weintraub present the new with FantoVision edge computers for 10GigE Vision, Camera Link and CoaXPress 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 Computer Vision combining FPGA and NVIDIA Jetson at Industrial Vision Days conference at VISION 2021 show in Stuttgart, Germany.

    Need More Information?

    Our team of experts is ready to help you find the perfect solution for your application needs.

    • Free technical consultation
    • Custom solution design
    • Quick response time
    • Expert engineering support

    Or contact us directly:

    info@gidel.com




      Quote
      Gidel
      Privacy Overview

      This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.