IP Library › Granted Patent US 12,469,337
Granted Patent B2
US 12,469,337 · App. 18/322,710 · Granted Nov 11, 2025

System and method for vessel identification

Inventors: Ana Luisa Alfaro Suzan (North York, CA); Robert Michael Marshy (Ottawa, CA); Joshua Rabalao (Kanata, CA); Kasra Azizbaigi (Toronto, CA); Colin John Robertson (Gabriola Island, CA); Ramin Heydarlaki (Kelowna, CA)
Assignee: Global Spatial Technology Solutions Inc.
G07C5/008G06N3/0464
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,469,337
App. No.
18/322,710
Granted
Nov 11, 2025
Kind
B2
Abstract

Computer implemented methods, systems, and computer-readable media for predicting a vessel identifier are provided. These include providing, at a memory, a vessel identification model, receiving, at a processor in communication with the memory, vessel data from one or more sources, determining, at the processor, a plurality of periodograms from the vessel data, the plurality of periodograms determined for a candidate vessel corresponding to candidate vessel data in the vessel data, determining, at the processor, a spectrogram based on the plurality of periodograms; and predicting, at the processor, a vessel identifier output of the candidate vessel based on the spectrogram and the vessel identification model.

Claims (47)

1 . A computer implemented method for predicting a vessel identifier, the method comprising:

providing, at a memory, a vessel identification model generated based on historical vessel tracking data for a plurality of vessels;

receiving, at a processor in communication with the memory, vessel data from one or more sources;

determining, at the processor, a plurality of periodograms from the vessel data, the plurality of periodograms determined for a candidate vessel corresponding to candidate vessel data in the vessel data;

determining, at the processor, a spectrogram based on the plurality of periodograms; and

predicting, at the processor, a vessel identifier output of the candidate vessel based on the spectrogram and the vessel identification model, wherein the vessel identifier output associates the candidate vessel with at least one of the plurality of vessels.

2 . The method of claim 1 , wherein each of the plurality of periodograms is determined for the candidate vessel using a sliding window passed over the candidate vessel data.

3 . The method of claim 1 , wherein the plurality of periodograms are determined for the candidate vessel based on a time-domain to frequency-domain transformation applied to the candidate vessel data.

4 . The method of claim 3 , wherein the time-domain to frequency-domain transformation comprises a floating-mean Lomb-Scargle periodogram (FMLSP) algorithm.

5 . The method of claim 1 , wherein the spectrogram comprises a two-dimensional bitmap, the two dimensional bitmap comprising a time axis and a frequency axis and optionally wherein each pixel of the two-dimensional bitmap comprises a magnitude of the corresponding periodogram for that time and frequency and optionally wherein the two-dimensional bitmap comprises has a color depth of 1 bit per pixel, 2 bits per pixel, 4 bits per pixel, 8 bits or 32 bits per pixel.

6 . The method of claim 1 , wherein the vessel data comprises at least one selected from the group of satellite AIS data from a satellite AIS data source, and vessel information data from a vessel information source and optionally wherein the vessel data comprises at least one selected from the group of course-over-ground data, time of transmission data, magnitude of transmission power data, and phase of transmission power data.

7 . The method of claim 1 , further comprising:

receiving, at the processor, environmental data from the one or more sources; and

wherein the vessel identifier output of the candidate vessel is predicted based on the environmental data, the spectrogram and the vessel identification model and optionally wherein the environmental data comprises at least one selected from the group of: wind speed, wind direction, wave height, wave frequency, ocean current and sea surface temperature.

8 . The method of claim 7 , further comprising:

associating the environmental data with the vessel data using a spatial-temporal join and optionally wherein the environmental data comprises at least one selected from the group of Marine Environment Monitoring Service and satellite data.

9 . The method of claim 1 , wherein the vessel identification model comprises a convolutional neural network.

10 . The method of claim 1 , wherein the vessel identification model comprises a vessel type classifier, a vessel size classifier, and a vessel identity classifier.

11 . The method of claim 10 , further comprising predicting, at the processor, a vessel type output of the candidate vessel based on the spectrogram and the vessel identification model.

12 . The method of claim 10 , further comprising predicting, at the processor, a vessel size output of the candidate vessel based on the spectrogram and the vessel identification model.

13 . The method of claim 1 , wherein the predicting, at the processor, a vessel identifier output of the candidate vessel comprises:

predicting, at the processor, a plurality of candidate vessel identifiers of the candidate vessel; and

selecting, at the processor, the vessel identifier output from the plurality of candidate vessel identifiers based on a voting classifier, the voting classifier electing the vessel identifier output based on vessel data.

14 . A computer-implemented system for predicting a vessel identifier, the system comprising:

a memory comprising a vessel identification model, the vessel identification model generated based on historical vessel tracking data for a plurality of vessels; and

a processor in communication with the memory, the processor configured to:

receive vessel data from one or more sources;

determine a plurality of periodograms from the vessel data, the plurality of periodograms determined for a candidate vessel corresponding to candidate vessel data in the vessel data;

determining a spectrogram based on the plurality of periodograms; and

predicting a vessel identifier output of the candidate vessel based on the spectrogram and the vessel identification model, wherein the vessel identifier output associates the candidate vessel with at least one of the plurality of vessels.

15 . The system of claim 14 , wherein each of the plurality of periodograms is determined for the candidate vessel using a sliding window passed over the candidate vessel data.

16 . The system of claim 14 , wherein the plurality of periodograms are determined for the candidate vessel based on a time-domain to frequency-domain transformation applied to the candidate vessel data.

17 . The system of claim 16 , wherein the time-domain to frequency-domain transformation comprises a floating-mean Lomb-Scargle periodogram (FMLSP) algorithm.

18 . The system of claim 14 , wherein the spectrogram comprises a two-dimensional bitmap, the two dimensional bitmap comprising a time axis and a frequency axis and optionally wherein each pixel of the two-dimensional bitmap comprises a magnitude of the corresponding periodogram for that time and frequency and optionally wherein the two-dimensional bitmap comprises has a color depth of 1 bit per pixel, 2 bits per pixel, 4 bits per pixel, 8 bits or 32 bits per pixel.

19 . The system of claim 14 , wherein the vessel data comprises at least one selected from the group of satellite AIS data from a satellite AIS data source, and vessel information data from a vessel information source and optionally wherein the vessel data comprises at least one selected from the group of course-over-ground data, time of transmission data, magnitude of transmission power data, and phase of transmission power data.

20 . The system of claim 14 wherein the processor is further configured to:

receive environmental data from the one or more sources; and

wherein the vessel identifier output of the candidate vessel is predicted based on the environmental data, the spectrogram and the vessel identification model; and optionally wherein the environmental data comprises at least one selected from the group of: wind speed, wind direction, wave height, wave frequency, ocean current and sea surface temperature.

21 . The system of claim 20 , wherein the processor is further configured to:

associate the environmental data with the vessel data using a spatial-temporal join; and optionally wherein the environmental data comprises at least one selected from the group of Marine Environment Monitoring Service and satellite data.

22 . The system of claim 21 , wherein the processor is further configured to predict a vessel type output of the candidate vessel based on the spectrogram and the vessel identification model.

23 . The system of claim 21 , wherein the processor is further configured to predict a vessel size output of the candidate vessel based on the spectrogram and the vessel identification model.

24 . The system of claim 14 , wherein the vessel identification model comprises a convolutional neural network.

25 . The system of claim 14 , wherein the vessel identification model comprises a vessel type classifier, a vessel size classifier, and a vessel identity classifier.

26 . The system of claim 14 , wherein the processor is further configured to predict a vessel identifier output of the candidate vessel comprises:

predicting, at the processor, a plurality of candidate vessel identifiers of the candidate vessel; and

selecting, at the processor, the vessel identifier output from the plurality of candidate vessel identifiers based on a voting classifier, the voting classifier electing the vessel identifier output based on vessel data.

Assignments (2)
SECURITY INTEREST Recorded Sep 22, 2025
From: GLOBAL SPATIAL TECHNOLOGY SOLUTIONS INC.
To: BDC CAPITAL INC.
Reel/Frame 072946/0181 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 6, 2024
From: ALFARO SUZAN, ANA LUISA; MARSHY, ROBERT MICHAEL; RABALAO, JOSHUA; AZIZBAIGI, KASRA; ROBERTSON, COLIN JOHN; HEYDARLAKI, RAMIN
To: GLOBAL SPATIAL TECHNOLOGY SOLUTIONS INC.
Reel/Frame 066668/0796 →
Continuity (1)
Related Publication 20240395076A1 · Nov 28, 2024
References Cited (54)
US 11151169B2 · Wroblewski · 2021 [cited by applicant]
US 20190120928A1 · O'Shea · 2019 [cited by examiner]
US 20200025958A1 · Kamil Amin · 2020 [cited by examiner]
US 20210387706A1 · Siganos · 2021 [cited by examiner]
US 20210390279A1 · Siganos · 2021 [cited by examiner]
US 20240394568A1 · Alfaro Suzan · 2024 [cited by examiner]
US 20240395076A1 · Alfaro Suzan · 2024 [cited by examiner]
CN 113316792A · 2021 [cited by applicant]
CN 115063676A · 2022 [cited by applicant]
EP 3029487 · 2016 [cited by applicant]
WO 2021221854A1 · 2021 [cited by applicant]
Marine Traffic: Global Ship Tracking, accessed Dec. 14, 2022 <https://web.archive.org/web/20221214143913/ https://www.marinetraffic.com/en/ais/home/centerx:-12.0/centery:25.0/zoom:4> (1 page). [cited by applicant]
Vessel Finder, accessed Dec. 15, 2022 <https://web.archive.org/web/20221209180941/https://www.vesselfinder.com/> (3 pages). [cited by applicant]
Zhou et al., “Ship classification based on ship behavior clustering from AIS data” Ocean Engineering 175 (2019) p. 176-187 (12 pages). [cited by applicant]
Amariei et al, “Grand Challenge : Cell Grid Architecture for Maritime Route Prediction on AIS Data Streams” 2018, p. 1-3 (3 pages). [cited by applicant]
Fossen, A survey on Nonlinear Ship Control: from Theory to Practice, (2000) IFAC Proceedings Volumes, vol. 33, Issue 21 (16 pages). [cited by applicant]
Greidanus H., A. M. (2013). Basin-Wide Maritime Awareness From Multi-Source Ship Reporting Data. TransNav, the International Journal on Marine Navigation and Safety of Sea Transportation, vol. 7, No. 2, doi:10.12716/100… [cited by applicant]
Harati-Mokhtari, A. W. (2007). Automatic Identification System (AIS): Data Reliability and Human Error Implications. Journal of Navigation, 60(3), pp. 373-389. doi:10.1017/S0373463307004298 (17 pages). [cited by applicant]
Liu, Z. (2017). Ship Adaptive Course Keeping Control With Nonlinear Disturbance Observer. IEEE Access, vol. 5, pp. 17567-17575, 2017. doi: 10.1109/Access.2017.2742001 (10 pages). [cited by applicant]
NASA Jet Propulsion Lab. (Apr. 25, 2007). MODIS Sea Surface Temperature (SST) Products. Retrieved from Physical Oceanography Distributed Active Archive Centre <https://web.archive.org/web/20201019213754/https://podaac-t… [cited by applicant]
Fossen & Perez (2009). Kalman Filtering for Positioning and Heading Control of Ships and Offshore Rigs. Estimating the Effects of Waves, Wind, and Current. IEEE Control System Magazine (15 pages). [cited by applicant]
Tomera, M. (2010). Nonlinear controller design of a ship autopilot. Applied Mathematics and Computer Science. 20. 271-280. 10.2478/v10006-010-0020-8 (11 pages). [cited by applicant]
Union, I. T. (2014). M.1371: Technical characteristics for an automatic identification system using time-division multiple access in the VHF maritime mobile band https://www.itu.int/rec/R-REC-M.1371-5-201402-l/en (148 p… [cited by applicant]
Westerdijk (2019). Classifying vessel types based on AIS data. Vrije Universiteit Amsterdam, Master Thesis. Business Analytics (86 pages). [cited by applicant]
S.-L. Hsieh, “Design Ensemble Machine Learning Model for Breast Cancer Diagnosis,” Springer Science, Aug. 3, 2011 (7 pages). [cited by applicant]
D. Optitz, “Popular Ensemble Methods: An Empirical Study,” Journal of Artificial Intelligence Research, pp. 169-198, Aug. 1999 (31 pages). [cited by applicant]
J. S. D. Opitz, “Generating Accurate and Diverse Members of a Neural-Network Ensemble,” Advances in Neural Information Processing Systems, (1996) MIT Press, pp. 535-543 (7 pages). [cited by applicant]
J. T. Vanderplas, “Understanding the Lomb-Scargle Periodogram,” The Astrophysical Journal Supplement Series, vol. 236, No. 1, May 11, 2018 (28 pages). [cited by applicant]
E. Cheever, “Introduction to the Fourier Transform,” Linear Physical Systems Analysis Swathmore College, 2005 [Online]. Available: https://lpsa.swarthmore.edu/Fourier/Xforms/FXformIntro.html (3 pages). [cited by applicant]
Press et al., “Numerical Recipes in C: The Art of Scientific Computing,” Oct. 1992 (1018 pages). [cited by applicant]
Rehfeld et al., “Comparison of correlation analysis techniques for irregularly sampled time series,” Apr. 5, 2011 (16 pages). [cited by applicant]
Lu &. Weng, “A survey of image classification methods and techniques for improving classification performance,” vol. 28:5, No. 823-870, 2007 (50 pages). [cited by applicant]
Shorten & Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J Big Data, vol. 6, p. 60, 2019 (49 pages). [cited by applicant]
Zhang et al,, “Audio Recognition using Mel Spectrograms and Convolution Neural Networks.,” (2019) Dept. of Electrical and Computer Engineering, University of California (5 pages). [cited by applicant]
Aslan et al., “Automatic detection of schizophrenia by applying deep learning over spectrogram images of EEG signals,” Traitement du Signal, vol. 37, pp. 235-244, 2020 (11 pages). [cited by applicant]
He (2016) Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (9 pages). [cited by applicant]
Kolen and Kremer, ““Gradient Flow in Recurrent Nets: The Difficulty of Learning LongTerm Dependencies,” in A Field Guide to Dynamical Recurrent Networks,” IEEE, pp. 237-243, 2001 (15 pages). [cited by applicant]
Dive Into Deep Learning, 8.6. Residual Networks (ResNet) and ResNeXt [Online], Dec. 2022 (11 pages) Available: https://d21.ai/chapter_convolutional-modern/resnet.html (11 pages). [cited by applicant]
Xie et al., “Aggregated Residual Transformations for Deep Neural Networks,” (2017) arXiv:1611.05431 (10 pages). [cited by applicant]
Szegedy et al., “Going Deeper with Convolutions,” (2014) arXiv:1409.4842 (12 pages). [cited by applicant]
Hu et al., “Squeeze-and-Excitation Networks,” (2019) arXiv:1709.01507 (13 pages). [cited by applicant]
Opitz and Maclin, “Popular Ensemble Methods: An Empirical Study,” Journal of Artificial Intelligence Research (1999) pp. 169-198 (30 pages). [cited by applicant]
S. Learn, “Scikit learn documentation,” (2011) [Online], Available: <https://scikit-learn.org/stable/modules/tree.html> (6 pages). [cited by applicant]
IBM, “What is a random forest IBM,” 2023. [Online] <https://www.ibm.com/topics/random-forest> (6 pages). [cited by applicant]
Tama & Rhee, “An extensive empirical evaluation of classifier ensembles for intrusion detection task,” Computer Systems Science and Engineering, 32(2):149-158, Mar. 2017 (11 pages). [cited by applicant]
Li et al., “VC-GAN: Classifying Vessel Types by Maritime Trajectories using Generative Adversarial Networks” 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI) p. 923-928 (6 pages). [cited by applicant]
Cumming et al., (1999). The Lick Planet Search: Detectability and Mass Thresholds. The Astrophysical Journal, 890-915 (26 pages). [cited by applicant]
Duhamel (1999). Fast Fourier Transforms: A Tutorial Review and a State of the Art. Digital Signal Processing Handbook. Ed. Vijay K. Madisetti and Douglas B. WilliamsBoca Raton: CRC Press LLC (51 pages). [cited by applicant]
Gatys (2016). Image Style Transfer Using Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (10 pages). [cited by applicant]
Lomb (1976). Least-squares frequency analysis of unequally spaced data. Astrophysics and Space Science, 447-462 (16 pages). [cited by applicant]
Ester (1996), A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise. Portland, Oregon: Proceedings of the Second International Confer… [cited by applicant]
Scargle (1982). Studies in astronomical time series analysis. II—Statistical aspects of spectral analysis of unevenly spaced data. The Astrophysical Journal, 835-853 (19 pages). [cited by applicant]
Verma (2018). Neural Style Transfer for Audio Spectograms, arXiv:1801.01589 (3 pages). [cited by applicant]
Jing (2020). Neural Style Transfer: A Review. IEEE Transactions on Visualization and Computer Graphics, 26(11):3365-3385 (26 pages). [cited by applicant]