Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links
2026-07-20 • Information Retrieval
Information RetrievalMachine LearningRobotics
AI summaryⓘ
The authors developed a way to quickly choose the most important underwater images taken by autonomous vehicles and send them over very slow communication links. Their method uses AI to pick either representative images or ones similar to a chosen picture, then compresses and transmits those images along with extra info about the full set. They tested this during three real missions near the UK and Gran Canaria with different vehicles. Their technique drastically reduces the data size—by about 400,000 times—allowing summaries of long missions to be sent in just over half an hour using low-bandwidth connections.
Autonomous Underwater Vehicle (AUV)Artificial Intelligence (AI)Image CompressionLow-bandwidth CommunicationSatellite CommunicationUnderwater ModemsImage SelectionData ReductionReal-time TransmissionMetadata
Authors
Adrian Bodenmann, Cailei Liang, Miquel Massot-Campos, Samuel Simmons, Alexander B. Phillips, Alberto Consensi, Matthew Kingsland, Rashiid Sherif, Stan Brown, Adam Riese, Blair Thornton
Abstract
This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best represent an entire dataset, or automatically finds the most similar images to a given query image for transmission to operators. Combined with metadata of a larger set of images, compressed versions of the selected images can be transmitted over satellite communication links or underwater modems, and provide operators on shore with information about the type of imagery the AUV is collecting while it is still deployed. Data from three deployments off the coast of the UK and in Gran Canaria using different AUVs and imaging systems demonstrate the method in the field. It achieved an almost 400,000-fold reduction in data volume compared to the raw data size, enabling transmission of data summaries of a 2-hour 47-minute-long mapping mission in just over 34 minutes over low-bandwidth satellite communication.