Vessel Classification through Convolutional Neural Networks using Passive Sonar Spectrogram Images
Open accessAbstract
Vessel classification is an extremely important task for coastal areas security and surveillance.Currently, this task relies on Synthetic Aperture Radar (SAR) images but gathering these images is expensive and often prohibitive.In this paper, we propose using spectrograms containing characteristic sound noise records of each vessel acquired from a single passive sonar device as an input to a convolutional neural network, which performs the classification.The main advantage of our method is its simplicity and low cost development due to the nature of this kind of data.Furthermore, our proposal can be used alongside other SAR-image-based method, potentially improving results of the overall classifier.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
When using spectrograms of hydrophone data, a basic four-convolutional-layer CNN has been shown to outperform a fully connected NN with either 0 or 512-neuron hidden layers.
“When using spectrograms of hydrophone data, a basic four-convolutional-layer CNN has been shown to outperform a fully connected NN with either 0 or 512-neuron hidden layers [119].”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [119]
The Results report that VesselNet achieved 83.9% average precision, exceeding the no-hidden-layer MLP’s 79.5% and the 512-neuron-hidden-layer MLP’s 79.7%. But the Experimental Procedure lists two convolutional layers in VesselNet, not four; its best-performing configuration also used both spectrogram and delta-frequency inputs. (LLM, conf=0.91)
Experimental — accuracy not yet measuredImproved results were observed when both spectrograms and delta frequency images were used as inputs over the use of spectrograms alone or in combination with delta-delta frequency images.
“Furthermore, improved results were observed when both spectrograms and delta frequency images (i.e., the first difference of signal features, an approximation of the first derivative) were used as inputs over the use of spectrograms alone or in combination with delta–delta frequency images (i.e., the second difference of signal features).”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [119]
Due to possible overfitting resulting from small dataset size, high interclass similarity, and a large number of model parameters, the finding about delta frequency images may have limitations.
“However, due to possible overfitting of the system resulting from small dataset size, high interclass similarity and a large number of model parameters, this finding may have limitations.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [119]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
(2010) · International Conference on Machine Learning · Cited by 13,995 · see citing works
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 7,048 · see citing works
Deep Reinforcement Learning: A Brief Survey
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2743240 · Cited by 4,733 · see citing works
Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80131-5 · Cited by 2,121 · see citing works
Environmental sound classification with convolutional neural networks
Piczak, K. J. (2015) · Machine learning for signal processing ... · doi:10.1109/mlsp.2015.7324337 · Cited by 971 · see citing works
High-Performance Neural Networks for Visual Object ClassificationPreprint
Ciresan, D. C., Meier, U., Masci, J., Gambardella, L. M., & Schmidhuber, J. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1102.0183 · Cited by 268 · see citing works
A modified faster R-CNN based on CFAR algorithm for SAR ship detection
Kang, M., Leng, X., Lin, Z., & Ji, K. (2017) · International Workshop on Remote Sensing with Intelligent Processing (RSIP) · doi:10.1109/rsip.2017.7958815 · Cited by 253 · see citing works
An evaluation of Convolutional Neural Networks for music classification using spectrograms
Costa, Y. M. G., Oliveira, L. S., & Junior, C. N. S. (2016) · Applied Soft Computing · doi:10.1016/j.asoc.2016.12.024 · Cited by 247 · see citing works
Automatic tagging using deep convolutional neural networksPreprint
Choi, K., Fazekas, G., & Sandler, M. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.00298 · Cited by 222 · see citing works
Ship Classification in Single-Pol SAR Images Based on Fuzzy Logic
Margarit, G., & Tabasco, A. (2011) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2011.2112371 · Cited by 122 · see citing works
Classification of ships using real and simulated data in a convolutional neural network
Ødegaard, N., Knapskog, A. O., Cochin, C., & Louvigné, J. C. (2016) · IEEE Radar Conference (RadarConf) · doi:10.1109/radar.2016.7485270 · Cited by 64 · see citing works
Ship-Iceberg Discrimination with Convolutional Neural Networks in High Resolution SAR Images
Bentes, C., Frost, A., Velotto, D., & Tings, B. (2016) · Cited by 61 · see citing works
Inside the spectrogram: Convolutional Neural Networks in audio processing
Dörfler, M., Bammer, R., & Grill, T. (2017) · International Conference on Sampling Theory and Applications · doi:10.1109/sampta.2017.8024472 · Cited by 57 · see citing works
Bentes, C., Velotto, D., & Lehner, S. (2015) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2015.7326627 · Cited by 45 · see citing works
A study on deep convolutional neural networks for computer vision applications
Filho, E., & de Moura, R. (2017) · Americanae (AECID Library) · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- R. G. V. Meyer, W. Kleynhans, and C. P. Schwegmann, "Small Ships don't Shine: Classification of Ocean Vessels from Low Resolution, Large Swath Area SAR Acquisitions," in 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2016-Novem. Beijing, China: IEEE, 2016, pp. 975-978.
- I. Macedo Quintanilha, "End-to-end Speech Recognition Applied to Brazilian Portuguese Using Deep Learning," Ph.D. dissertation, Federal University of Rio de Janeiro, 2017.
- I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, 1st ed. Cambridge, United States: MIT Press, 2016.
- J. B. d. O. S. Filho, "Classificação Neural de Sinais de Sonar Passivo," Ph.D. dissertation, Federal University of Rio de Janeiro, 2007.
Cited by
Sorted by citations
Domingos, L. C. F., Santos, P. E., Skelton, P. S. M., Brinkworth, R. S. A., & Sammut, K. (2022) · Sensors · doi:10.3390/s22062181 · Cited by 93 · see citing works
“When using spectrograms of hydrophone data, a basic four-convolutional-layer CNN has been shown to outperform a fully connected NN with either 0 or 512-neuron hidden layers [119].”
BackgroundMethodBarros, R. E. D. B. A., & Ebecken, N. F. F. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108778 · Cited by 26 · see citing works
Zhu, P., Zhang, Y., Huang, Y., Lin, B., Zhu, M., Zhao, K., & Zhou, F. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3329653 · Cited by 21 · see citing works
Kubicek, B., Gupta, A. S., & Kirsteins, I. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11030571 · Cited by 7 · see citing works
Rihawi, S., Mouti, S., Rasli, R. M., & Ariffin, S. A. (2023) · International Journal of e-Collaboration · doi:10.4018/ijec.316663 · Cited by 4 · see citing works
Najamuddin, Sheikh, U. U., & Sha’ameri, A. Z. (2025) · Measurement · doi:10.1016/j.measurement.2025.118494 · Cited by 3 · see citing works
Najamuddin, Sheikh, U. U., & Ameri, A. Z. S. (2025) · Archives of Acoustics · doi:10.24425/aoa.2025.153662 · Cited by 3 · see citing works
Deep Learning on Active Sonar Data Using Bayesian Optimization for Hyperparameter Tuning
Berg, H. S., & Hjelmervik, K. T. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412347 · Cited by 3 · see citing works
Transfer Learning for Distance Classification of Marine Vessels Using Underwater Sound
Wout, D., Deneudt, K., Parcerisas, C., Schall, E., & Debusschere, E. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3593779 · Cited by 2 · see citing works
Applying the majority voting rule in acoustic detection and classification of drones
Fernandes, R. P., Apolinário, J. A., Ramos, A. L. L., & Seixas, J. M. (2021) · Anais de XXXV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais · doi:10.14209/sbrt.2021.1570726624 · Cited by 2 · see citing works
Multidimensional Attention Convolution Plugin for Ship Radiated Noise Classification
Zheng, Z., & Liu, P. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7188-5_20
- Authors
- Cinelli, L., Chaves, G., & Lima, M.
- Venue
- Anais de XXXVI Simpósio Brasileiro de Telecomunicações e Processamento de Sinais
- Published
- 2018
- OpenAlex
- W2975338200
- Cited by
- 13
- References
- 18
- Citations by year
- 2025: 4 · 2023: 3 · 2022: 4 · 2021: 2
- FWCI
- 3.17
- Type
- conference paper
- Language
- pt
- Open access
- bronze
- doi.org
- Locations
- Anais de XXXV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (publishedVersion)
- Topics
- Physical Sciences › Earth and Planetary Sciences › Oceanography › Underwater Acoustics Research
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Wireless Signal Modulation Classification
- Keywords
- vessel classification, passive sonar, spectrogram images, convolutional neural networks, coastal monitoring, maritime security
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
