Image enhancement AI technology that performs deep learning optimized for underwater subjects

Kawasaki, Japan, November 26, 2025

Fujitsu today announced the development of a technology for rapidly and accurately quantifying blue carbon, i.e., carbon absorbed and stored by marine and coastal ecosystems, from seaweed and seagrass, supporting the restoration and conservation of seagrass beds. This innovation, part of Fujitsu's research and development into ocean digital twin technology, significantly accelerates the certification process for blue carbon credits, a key initiative in decarbonization and marine environmental preservation.

The newly developed technology enables data collection, measurement, ecosystem recognition, blue carbon quantification, and support for recovery and conservation activities without requiring specialized experts. The system has been validated to measure and recognize with over 85% accuracy and quantify blue carbon in areas exceeding 1 hectare, in 1/100th of the time previously required (i.e., approximately 30 minutes per hectare).

The technology’s effectiveness was confirmed through the attainment of J-Blue Credit® [1] certification, receiving a distinguished 95% accreditation rate.

Moving forward, Fujitsu will apply the developed technologies and system to real marine areas. In collaboration with Japanese local governments and businesses, the company will promote their use in seagrass bed restoration and conservation, and J-Blue Credit certification, aiming to achieve nature-positive outcomes. Additionally, Fujitsu will expand the application scope of the developed technologies to include inspections of marine facilities such as offshore wind power generation, which is expected to contribute to decarbonization, and environmental surveys before and after marine construction. By advancing ocean digital twin technology and building partnerships with companies, local governments, and organizations engaged in carbon neutrality and biodiversity conservation, Fujitsu aims to realize businesses that balance environmental preservation and economic growth by 2027.

To solve this in real-time underwater, Fujitsu turned to an unlikely technology – a “Judging Support System” designed in collaboration with the International Gymnastics Federation to assist in gymnastics judging. With the help of AI, this system uses 3D sensors and AI to assist judges with capturing and properly assessing the complex movements of gymnasts. While pairing this technology with underwater research may seem strange, it’s actually quite sensible. The AUV must move around in constantly sloshing water, and this adapted gymnastics system enables high-resolution and high-speed scanning of the underwater environment.

The gymnastics judging system was also supported by an underwater Light Detection And Ranging (LiDAR) device which allows users to choose among three laser wavelengths to find the optimal measuring wavelength based on sea conditions. This will allow for the measurement of three dimensions from an autonomous unmanned submarine in motion as well as the development of technologies that will track moving objects.

About the developed technology

1. Image enhancement AI technology that restores the color and contour of underwater subjects

Fujitsu developed an image enhancement AI technology that performs deep learning optimized for underwater subjects to create high-resolution 3D images of underwater organisms and structures, even from images taken from murky water where the color is distorted and the contours of objects are blurred. This technology consists of two types of AI—one that achieves turbidity removal and contour restoration, correcting the original color of the subject and improving the blurred contours of target objects to generate enhanced images before 3D conversion. This prevents errors during 3D processing and subject recognition, making it possible to measure the shape of each object.

Currently, BLUABLE is conducting field trials for seaweed bed cultivation at 16 undersea locations in Japan.

The company plans to verify more advanced measuring techniques for blue carbon using IoT and AI.

Fujitsu will provide its technology to BLUABLE, including its ocean digital twin, as it works toward preserving the world’s marine environment. In addition, through FIC, Fujitsu will continue contributing to a sustainable society by fostering talent and businesses that can take on the challenge of resolving societal issues.

Currently, BLUABLE is conducting field trials for seaweed bed cultivation at 16 undersea locations in Japan.

The company plans to verify more advanced measuring techniques for blue carbon using IoT and AI.

Fujitsu will provide its technology to BLUABLE, including its ocean digital twin, as it works toward preserving the world’s marine environment. In addition, through FIC, Fujitsu will continue contributing to a sustainable society by fostering talent and businesses that can take on the challenge of resolving societal issues.

Competitive Landscape And Partnerships

Several giants now chase orbital compute supremacy. Blue Origin synergy with Amazon’s cloud assets could accelerate vertical integration. Meanwhile, Google leverages in-house TPUs and optical networking research to advance Project Suncatcher.

Starcloud and Crusoe target early revenue by selling remote GPU hours from pilot satellites. Moreover, Nvidia supports their roadmap through hardware validation and marketing. Consequently, investors view orbital computing infrastructure as a potential moat for differentiated cloud offerings.

SpaceX: cutting launch prices with reusable boosters and Starship.

Planet Labs: providing imaging heritage and bus hardware for Suncatcher prototypes.

Regulators: crafting debris, frequency, and export-control rules.

Any misalignment could strand orbital computing infrastructure assets for years. Nevertheless, partnership complexity also creates execution risk. Therefore, robust commercial contracts and shared standards become crucial.

Furthermore, Blue Origin synergy may deliver dedicated New Glenn flights tuned for heavy data center payloads.

The ecosystem spans launch, hardware, software, and policy actors. However, success hinges on tightly synchronized roadmaps.

Subsequently, enterprises planning adoption need a structured decision framework.

Therefore, we conclude with strategic guidance for technology leaders.

By - Aaradhay Sharma