Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 20;25(6):1930.
doi: 10.3390/s25061930.

Enhancing Maritime Domain Awareness Through AI-Enabled Acoustic Buoys for Real-Time Detection and Tracking of Fast-Moving Vessels

Jeremy Karst  1 , Robert McGurrin  2 , Kimberly Gavin  2 , Joseph Luttrell  1 , William Rippy  1 , Robert Coniglione  1 , Jason McKenna  1 , Ralf Riedel  1
Affiliations

Enhancing Maritime Domain Awareness Through AI-Enabled Acoustic Buoys for Real-Time Detection and Tracking of Fast-Moving Vessels

Jeremy Karst et al. Sensors (Basel). .

Abstract

Acoustic target recognition has always played a central role in marine sensing. Traditional signal processing techniques that have been used for target recognition have shown limitations in accuracy, particularly with commodity hardware. To address such limitations, we present the results of our experiments to assess the capabilities of AI-enabled acoustic buoys using OpenEar™, a commercial, off-the-shelf, software-defined hydrophone sensor, for detecting and tracking fast-moving vessels. We used a triangular sparse sensor network to investigate techniques necessary to estimate the detection, classification, localization, and tracking of boats transiting through the network. Emphasis was placed on evaluating the sensor's operational detection range and feasibility of onboard AI for cloud-based data fusion. Results indicated effectiveness for enhancing maritime domain awareness and gaining insight into illegal, unreported, and unregulated activities. Additionally, this study provides a framework for scaling autonomous sensor networks to support persistent maritime surveillance.

Keywords: OpenEar™; acoustic target recognition; artificial intelligence; localization; marine domain awareness (MDA).

PubMed Disclaimer

Conflict of interest statement

Authors Robert McGurrin and Kimberly Gavin were employed by the company BlueIQ. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
BlueIQ OpenEar™ sensor data collection area; the test boat path is shown by red dashed lines, the sensor locations by blue triangles, and the starting points for each test event by black circles. The test range is shown in (a),the deployment operation for the 3 OpenEar™ buoys in (b), and a zoomed view in (c).
Figure 2
Figure 2
BlueIQ OpenEar™ sensor data capture, processing, and deployment pipeline.
Figure 3
Figure 3
GCC-PHAT correlation from example signal between each pair of three microphones.
Figure 4
Figure 4
Localization estimate for an example signal using Generalized Cross-Correlation with Phase Transform.
Figure 5
Figure 5
Real-time detection of vessel by AI model running on OpenEar™.
Figure 6
Figure 6
Reprocessed data after algorithm tuning showing extended detection ranges.
Figure 7
Figure 7
Acoustic waveforms and high-resolution spectrograms for watercraft; each row represents a different buoy microphone; blue are low intensity signals, red are low. Column 1 (A1,B1,C1) is the audio waveform showing a cleaner waveform for (A1), column 2 (A2,B2,C2) is a full-frequency spectrogram showing weaker frequency for microphone (B2), and column 3 (A3,B3,C3) shows a narrow-band, high-resolution spectrogram where microphone (C3) is noisiest.
Figure 8
Figure 8
Initial TDOA estimation results.
Figure 9
Figure 9
Initial position inferences from TDOA results; X and Y position of similar accuracy (A); actual and estimated distance show medium noise level (B); confidence shows most point within threshold (C).
Figure 10
Figure 10
Confidence-weighted and -filtered TDOA results in high-confidence region.
Figure 11
Figure 11
Final localization results.
See this image and copyright information in PMC

References

    1. Pollara A., Sutin A., Salloum H. Passive Acoustic Methods of Small Boat Detection, Tracking and Classification; Proceedings of the 2017 IEEE International Symposium on Technologies for Homeland Security (HST); Waltham, MA, USA. 25–26 April 2017; pp. 1–6.
    1. Kavitha R., Thayaambika M., Malini P.V., Almelu N. Passive Sensing and Detection of Boats along Coastline Using Static Sensors; Proceedings of the 2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS); Chennai, India. 4–5 May 2017; pp. 474–479.
    1. Ng Y., Pereira J.M., Garagic D., Tarokh V. Robust Marine Buoy Placement for Ship Detection Using Dropout K-Means; Proceedings of the ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); Barcelona, Spain. 4–8 May 2020; pp. 3757–3761.
    1. Lal S., Arora M.K., Riswandi B.A., Singh N., Singh B. AI Applications for Clean Energy and Sustainability. IGI Global; Hershey, PA, USA: 2024. Melding Artificial Intelligence and Remote Sensing Data for Real-Time Monitoring of Marine Biodiversity; pp. 299–319.
    1. Dogan G., Vaidya D., Bromhal M., Banday N. Chapter 14—Artificial Intelligence in Marine Biology. In: Hamadani A., Ganai N.A., Hamadani H., Bashir J., editors. Guide to Artificial Intelligence. Academic Press; Cambridge, MA, USA: 2024. pp. 241–254.

LinkOut - more resources