Meet us next:
Space Tech Expo
Meet us next:
Space Tech Expo
All events

Enable raw imagery & accelerate space-to-ground data transmission for Earth Observation

Power-efficient raw image compression for satellite manufacturers, optical mission operators and satellite image data users.
Improve accuracy of AI/ML analysis
Save costs & bring out the most of your satellite imagery
Increase raw image data throughput onboard
Maximise storage onboard
original raw dataset
compressed raw dataset
Compression ratio
Typically 6:1
Compression speed
200-6400 Mpx/s
1.6 GB/s
Intel I9 14900K, Windows, 4 threads
Data quality
no artefacts
no bias
no filtering

Large image data in the way of satellite data analysis


In aerospace, onboard image sensors generate extensive data volumes, resulting in slow data transmission, high energy consumption, and costly infrastructure. Optimizing raw image data workflows for satellite imagery is crucial for advancing Earth Observation and maximizing AI/ML potential.

Existing solutions don't fit AI/ML

Conventional lossless compression is slow and provides a limited compression ratio, failing to address scalability concerns. Meanwhile, visually lossless algorithms jeopardize the robustness of ML models in the context of AI-driven analysis of Earth Observation image data, especially in applications like environmental monitoring, geospatial analysis, and aerial agriculture data.

workflow issues

Jetraw Core — Unlock the true power of satellite images


Jetraw Core stands as a high-efficiency raw image compression solution. It seamlessly integrates into FPGA IP Core or functions as software within data centers. This integration significantly enhances the transmission speed of raw image data while preserving the utmost data quality, thereby ensuring scalable and dependable AI analysis.


Jetraw Core addresses the challenges associated with every step of the aerospace image workflow. It excels in energy efficiency and infrastructure optimization, leading to substantial advantages for both satellite manufacturers and Earth observation data users.

Two implementation routes

Integrate as FPGA IP Core in the system to increase data processing speed & reduce compute requirements
Integrate as a software library to maximise your IT infrastructure and save on storage and increase transfer speed


High speed
High ratio
Raw quality
No artifacts
Tailored for AI

Enable scalable raw image data management for robust AI processing of EO data

Faster acquisition & I/O

Acquire and transmit raw satellite image data faster between memory, FPGA, CPU, onboard, remote and cloud storage, using existing cable and network

Higher throughput

Achieve a higher raw image data throughput rate (measured in FPS, MB/s, and Mpx/s) with low latency, while conserving computational and bandwidth resources.

Lower energy consumption

Reduce CO2 emissions related to image data by using smaller storage volumes, efficient logistics, and lower power consumption from payload to ground stations and data centers.

Lower costs & optimised infrastructure

Maximize image downloads within a single downlink, enabling quicker, more cost-effective, and environmentally friendly distribution and storage of Earth Observation image data on the ground.

Accurate data for reliable AI

Jetraw provides format-agnostic raw image quality output. The quality of image data directly impacts the accuracy of ML models and AI-based results of Earth Observationdata.

Test your AI application at a fraction of data acquisition costs

Generate synthetic image data from auto-labelled aerial & drone images to achieve ML results with better-than-human performance
Get in touch to improve your data performance and reduce costs

Clients and Partners

“With the world relying on remote sensing satellite data, there’s a paradigm shift from ‘raw data delivery’ to ‘information delivery’. But those daily petabytes come at a high cost.

Dotphoton preserves the image quality of our data while attaining high compression ratios, which was only possible with high information loss in the past. This allows storing full information, and processing it faster”

Roberto Camarero,
Onboard Payload Data Processing Engineer European Space Agency
Integration type
High throughput, low latency, power-efficient raw compression on FPGA
Fast, easily integrated in-camera raw compression as a software
5–10:1 compression ratio
Indistinguishable from raw, interoperable
CMOS, sCMOS, CCD camera support
Mono, Bayer and other CFA image sensors support
No bias, no artifacts, no artificial correlations, no low pass filtering
Tightly-controlled image quality 1.2dB SNR equiv. increase ISO100→ISO115
Image data
  • 16-bit images
  • Configurable image dimensions
Raw image buffer or common file formats
  • 1 to 32 pixels per clock cycle
  • Up to 200 MHz clock frequency
  • Low latency (~1-line, 2-lines for Bayer)
  • 200MB /s/core
  • Multi-threading support
Integration features
  • Backpressure support
  • This is some text inside of a div block.
  • From 3968 LUT for single core compressor to 70790 for 32 pixels
  • AXI4-stream data interface
  • Available as a software library / codec
  • Callable from C, C++, C#, Java, Python
System support
  • Xilinx FPGAs
  • Intel on request
  • Intel, AMD and ARM CPU support
  • Linux, Windows and Mac support

Take next steps to maximise the value of your image data