Draft:FlyPix

Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL Easy tools: Citat…

Draft:FlyPix
FlyPix
TypePrivate
IndustryEarth observation, Geospatial analysis
HeadquartersDarmstadt, Germany
Key people
Ivan Tankoyeu, Sergey Sukhanov
Websiteflypix.ai

FlyPix (also known as FlyPix AI GmbH) is a German technology company based in Darmstadt that specializes in earth observation (EO)[1] and artificial intelligence analytics.[2] The company provides a platform that enables users to analyze satellite, aerial, and drone imagery.[3] FlyPix has also partnered with the European Space Agency,[4][2] NVIDIA, Amazon Web Services,[5] and Google.[6]

History

FlyPix AI GmbH was established by Sergey Sukhanov and Ivan Tankoyeu, researchers with extensive backgrounds in remote sensing, computer vision, and machine learning.[7] The company became part of the European Space Agency Business Incubation Centre (ESA BIC) Hessen network in 2023–2025.[2] It also received support from ESA's InCubed programme to further develop its "AI Visual Copilot" technology, which focuses on utilizing Earth observation data. The technology was later renamed as Orion Find Similar.[7]

In 2024, FlyPix AI won the Prototype Track of the CASSINI Challenges, a competition organized by the European Union Agency for the Space Programme (EUSPA).[8] It was also recognized by the INNOspace Masters competition in Germany.[9]

Technology

The company's primary product is the FlyPix AI platform, a tool designed to democratize access to geospatial analytics.[9][10] The platform's core feature, Orion Find Similar, utilizes one-shot learning and AI-assisted data annotation to train custom computer vision models, enabling automated object detection and image segmentation. By artificially generating training examples and using an active learning approach, the platform reduces the data labelling requirements and development time typically needed to build custom AI models.[7][11]

Core technologies include the Orion Find Similar, which identifies similar objects across large imagery based on a single user-provided example; Orion SmartSeg, an engine that generates high-quality semantic segmentation masks with minimal input; and GeoSense, a conversational spatial intelligence module that enables users to interact with complex vector data through a natural language, chat-based interface.[2][12]

The software supports various data sources from satellite imagery, drones,[13] and aerial photography,[14] including RGB, multispectral, and hyperspectral imagery. It is used for various applications such as monitoring agricultural land for issues such as crop diseases,[15] mapping marine pollution,[16] detecting illegal waste disposal, tracking deforestation and wildfires,[17] monitoring biodiversity,[18] and assessing infrastructure damage.[9][19]

In addition, FlyPix has written articles about space debris mapping.[20][21]

Projects and applications

FlyPix AI's technology has been utilized in environmental monitoring and international climate action initiatives. In a notable project highlighted by the United Nations Office for Outer Space Affairs (UNOOSA) and UN-SPIDER, FlyPix AI collaborated with climate change authorities to detect and map palm trees across the island of Tongatapu.[22] Utilizing Airbus Pléiades Neo satellite imagery at a 15-centimeter resolution, the platform's deep learning models achieved a detection accuracy of 94.7%. The resulting inventory assisted Tonga in establishing baselines for carbon sequestration, which supports carbon credit estimation and greenhouse gas reporting under the United Nations Framework Convention on Climate Change (UNFCCC).[22]

References

  1. ^ "ICLR Synthetic data augmentation for earth observation object detection tasks" (PDF). ICLR. Retrieved 2026-06-08.
  2. ^ a b c d "FlyPix AI - ESA Commercialisation Gateway". European Space Agency. Retrieved 2026-06-02.
  3. ^ "Φ-lab-WMF AI4EO competition inspires European New-Space start-ups to rise to the challenge". Φ-lab-WMF AI4EO competition inspires European New-Space start-ups to rise to the challenge. 2021-02-19. Retrieved 2026-06-08.
  4. ^ Ebel, Patrick; Schneider, Rochelle; Bonavita, Massimo; Clare, Mariana; Jungbluth, Anna; Pourshamsi, Maryam; Chantry, Matthew; Alexe, Mihai; Sebastianelli, Alessandro; Chrust, Marcin (2024-10-09). "2024 ESA-ECMWF workshop report: current status, progress and opportunities in machine learning for Earth system observation and prediction". npj Climate and Atmospheric Science. 7 (1). doi:10.1038/s41612-024-00757-4. ISSN 2397-3722. Retrieved 2026-06-08.
  5. ^ "AWS Marketplace: FlyPix AI Geospatial Analysis Platform". Amazon Web Services. 2026-01-12. Retrieved 2026-06-08.
  6. ^ "Space AI is Having a Moment". Payload Space. Retrieved 2026-06-02.
  7. ^ a b c "AI Visual Copilot | InCubed". ESA InCubed. Retrieved 2026-06-02.
  8. ^ "2024 CASSINI Challenges winners". EU Agency for the Space Programme. 2025-07-14. Retrieved 2026-06-02.
  9. ^ a b c "FlyPix AI – Democratising Earth observation for a sustainable future". INNOspace Masters. Retrieved 2026-06-02.
  10. ^ Kumar, Muthu (2025-01-31). "Global Top 100 Geospatial Companies". Geoawesome. Retrieved 2026-06-08.
  11. ^ "Activity: ‪Ai Visual Copilot‬". Activities Platform. 2015-09-01. Retrieved 2026-06-08.
  12. ^ "FlyPix AI Tutorials: Product Features & How-To Guides". YouTube. 2024-03-06. Retrieved 2026-06-08.
  13. ^ Al Shukaili, Khalifa; Mufarraji, Said Al; Al kindi, Hamza (2024-12-01). Investigate and Build FPV (First Person View) Drone for Various Applications to Serve Oman Needs with Respect to Cost and Efficiency. IEOM Society International. doi:10.46254/GC02.20240052. ISBN 979-8-3507-4442-2. Retrieved 2026-06-08.
  14. ^ "FlyPix AI: Unlocking the Future of Intelligent Navigation and Geospatial Analysis". Skypage. 2026-02-13. Retrieved 2026-06-08.
  15. ^ Shafay, Muhammad; Hassan, Taimur; Owais, Muhammad; Hussain, Irfan; Khawaja, Sajid Gul; Seneviratne, Lakmal; Werghi, Naoufel (2025-10-28). "Recent advances in plant disease detection: challenges and opportunities". Plant Methods. 21 (1). doi:10.1186/s13007-025-01450-0. ISSN 1746-4811. PMC 12570820. PMID 41152989.
  16. ^ محمود, عبد الحكيم (2023-12-10). "الذكاء الاصطناعي ينجح في الكشف عن البلاستيك في المحيطات". الجزيرة نت (in Arabic). Retrieved 2026-06-08.
  17. ^ Thapa, Pawan (2026). "Assessing wildfire severity and identifying hotspots using computational intelligence and image processing". Computational Intelligence in Surveillance Systems Using Image Processing. Elsevier. p. 161–172. doi:10.1016/b978-0-443-36408-2.00003-5. ISBN 978-0-443-36408-2. Retrieved 2026-06-08.
  18. ^ Dinesh Deckker; Subhashini Sumanasekara (2025-03-01). "Systematic Review: AI for Wildlife Conservation - Preventing Elephant Deaths from Train Collisions Using Artificial Intelligence". EPRA International Journal of Environmental Economics, Commerce and Educational Management: 78–98. doi:10.36713/epra20403. ISSN 2348-814X. Retrieved 2026-06-08.
  19. ^ "10 Best AI Tools for Environmental Monitoring". Unite.AI. Retrieved 2026-06-02.
  20. ^ Lee, Hoonhee; Shin, Dongwoo; Hong, Seongin; Choi, Joon-Min; Ju, Gwanghyeok. "Recent trends in AI technology applications and related policies in the space security industry". Journal of Space Security. 2 (2). 한국우주안보학회: 62–82. doi:10.23386/JOSS.2025.2.2.006.
  21. ^ "Обломки ракет и спутников: откуда в космосе появляется мусор и как его оттуда убрать". forbes.ru (in Russian). Retrieved 2026-06-08.
  22. ^ a b "Palm Tree Detection in Tongatapu for Carbon Credit Estimation". UN-SPIDER Knowledge Portal. Retrieved 2026-06-02.
This page will be placed in the following categories if it is moved to the article namespace.
Categories:

Content Disclaimer

Informasi ini disarikan dari Wikipedia dan disajikan kembali untuk tujuan edukasi. Konten tersedia di bawah lisensi CC BY-SA 3.0. Kami tidak bertanggung jawab atas ketidakakuratan data yang bersumber dari kontribusi publik tersebut.

  1. The information displayed on this website is sourced in part or in whole from Wikipedia and has been adapted for the purpose of restating it. We strive to provide accurate and relevant information, however:
  2. There is no guarantee of absolute accuracy. Wikipedia is an open, collaborative project that can be edited by anyone, so information is subject to change.
  3. It is not intended to constitute professional advice. The content displayed is for informational and educational purposes only. For important decisions (e.g., medical, legal, or financial), please consult a professional.
  4. Content copyright. Wikipedia is licensed under the Creative Commons Attribution-ShareAlike License (CC BY-SA). This means that content may be reused with appropriate attribution and shared under a similar license.
  5. Responsible use. Any risk arising from the use of information from this website is entirely the responsibility of the user.