Vessel Classification through Convolutional Neural Networks using Passive Sonar Spectrogram Images

Cinelli, Lucas Pinheiro; Chaves, Gabriel S.; Lima, Markus V. S.

doi:10.14209/sbrt.2018.340

Cited by 6 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second type of layer is the pooling layers which aggregate information they receive from the filter layers. They shrink the image dimension to a predetermined value by replacing all the information presented into one pool with a single value, mostly by its maximum or average (Cinelli et al, 2018). The figure (1) below describes the general design of the CNN.…”

Section: Literature Reviewmentioning

confidence: 99%

Virtual Teaching Assistant for Capturing Facial and Pose Landmarks of the Students in the Classroom Using Deep Learning

Rihawi

Mouti

Rasli

et al. 2023

International Journal of E-Collaboration

View full text Add to dashboard Cite

This research focuses on the learning challenges that both students and teachers face during the learning process. It addresses the different techniques and methods used for face recognition. The proposed VTA model uses the convolutional neural networks to recognize the identities of the student. It gathers the facial expressions and body poses of each student in the classroom and predicts the attention level of that student, thus determining his/her learning capabilities. This research will help the students achieve their learning objectives by being able to get an accurate and real evaluation of their contribution and attention during the classes. Also, the proposed VTA model helps the teacher get some insight into his/her teaching methodologies during the class as the model will observe and record the attentiveness of the students. This research will have a significant positive impact on student success and on effective lecturing.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Virtual Teaching Assistant for Capturing Facial and Pose Landmarks of the Students in the Classroom Using Deep Learning

Rihawi

Mouti

Rasli

et al. 2023

International Journal of E-Collaboration

View full text Add to dashboard Cite

show abstract

“…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 ]. 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).…”

Section: Machine Learning For the Classification Of Underwater Acoust...mentioning

confidence: 99%

A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance

Domingos

Santos

Skelton

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper presents a comprehensive overview of current deep-learning methods for automatic object classification of underwater sonar data for shoreline surveillance, concentrating mostly on the classification of vessels from passive sonar data and the identification of objects of interest from active sonar (such as minelike objects, human figures or debris of wrecked ships). Not only is the contribution of this work to provide a systematic description of the state of the art of this field, but also to identify five main ingredients in its current development: the application of deep-learning methods using convolutional layers alone; deep-learning methods that apply biologically inspired feature-extraction filters as a preprocessing step; classification of data from frequency and time–frequency analysis; methods using machine learning to extract features from original signals; and transfer learning methods. This paper also describes some of the most important datasets cited in the literature and discusses data-augmentation techniques. The latter are used for coping with the scarcity of annotated sonar datasets from real maritime missions.

show abstract

“…In this work, we try to solve the problem of detecting and classifying a single target [22] using audio signals collected from a drone, using a single microphone. The receiver device used to collect the signals in the AIRA-UAS corpus [23] is connected of a microphone array aboard a DJI Matrice 100 drone.…”

Section: A Problem Statement and Assumptionsmentioning

confidence: 99%

Applying the majority voting rule in acoustic detection and classification of drones

Fernandes¹,

Apolinario²,

Ramos³

et al. 2021

Anais Do XXXIX Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

This paper discusses an approach to target detection and classification based on acoustic signals collected using one single microphone. This study has applications to sonar or any other sound event classification system. We divide the problem into two parts, namely feature extraction and target detection and classification. We use an optimization step based on human auditory uncertainty. We employ a majority voting rule for every set of feature vectors, i.e., an estimate is only performed if the majority agrees. We conducted experiments using a single channel of the AIRA-UAS dataset, a public database of raw drone noises collected with an array of microphones mounted on a drone. This dataset comprises many different kinematics, with different spectra. The features we used are based on the Mel-Frequency Cepstral Coefficients (MFCC) and the Short-Time Fourier Transform of raw signals. We used the K-Nearest Neighbors algorithm for classification and adopted the crossvalidation strategy to evaluate the method. We observed that the use of MFCC results in less biased estimations, which favors the voting strategy. The detection in the proposed method reached a probability of false positive near 0%, even with a small set of votes, and a classification accuracy of 99.1%. These metrics satisfy the requirements of most civilian and military applications.

show abstract

Vessel Classification through Convolutional Neural Networks using Passive Sonar Spectrogram Images

Cited by 6 publications

References 11 publications

Virtual Teaching Assistant for Capturing Facial and Pose Landmarks of the Students in the Classroom Using Deep Learning

Virtual Teaching Assistant for Capturing Facial and Pose Landmarks of the Students in the Classroom Using Deep Learning

A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance

Applying the majority voting rule in acoustic detection and classification of drones

Contact Info

Product

Resources

About