A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
We propose a novel method for generating realistic-looking sonar side-scans of full-length missions, called Markov Conditional pix2pix (MC-pix2pix). ...
Producing realistic synthetic sonar imagery is a challenging problem as the model has to account for specific artefacts of real acoustic sensors, vehicle altitude, and a variety of environmental factors ...
ACKNOWLEDGMENT We thank Stephanos Loizou and Peter Scanlon for their help with the ATR experiments, and Roshenac Mitchell, Joshua Smith, and Henry Gouk -for the technical support; as well as all the participants ...
arXiv:1910.06750v2
fatcat:w2atb6zr4jbdlozmnvg5izclpy
Underwater Sonar Image Classification Using CWGAN-GP&DR And Improved Convolutional Neural Network
2020
IET Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This study presents a generative adversarial network (GAN) called conditional Wasserstein GAN-gradient penalty (CWGAN-GP)&DenseNet and ResNet, and a convolutional neural network (CNN) called improved CNN ...
Finally, compared with other methods, the CWGAN-GP&DR generate better underwater sonar images and effectively expand the underwater sonar image data set. ...
Acknowledgments The authors are grateful to the guest editors and anonymous reviewers for their constructive comments based on which the presentation of this paper has been greatly improved. ...
doi:10.1049/iet-ipr.2019.1735
fatcat:rq4v2u5o2ba3zja4xl7pssmhqi
Underwater acoustic signal analysis: preprocessing and classification by deep learning
2020
Neural Network World
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Then, among these methods, we modified a neural network(LeNet) to fit the dataset that is transformed by the spectrum to improve the classification accuracy. ...
To solve those problems, we firstly evaluated four popular spectrums (Audio Spectrum, Image Histogram, Demon and LOFAR) for data preprocessing and selected the best one that is suitable for the neural ...
Researchers have done a lot of work in related area like the classification for marine animals and some unpredictable noise generated by objects. ...
doi:10.14311/nnw.2020.30.007
fatcat:fcrooj2nana5rgqhtfzyxynga4
A Review on Deep Learning-Based Approaches for Automatic Sonar Target Recognition
2020
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper will be of great assistance for upcoming scholars to start their work on sonar automatic target recognition. ...
With the rapid development in science and technology, the advancement in sonar systems has increased, resulting in a decrement in underwater casualties. ...
Acknowledgments: The authors would like to appreciate sonar systems researchers for their hard work, without which the rapid development in the sonar ATR would not be possible. ...
doi:10.3390/electronics9111972
fatcat:uuiprlwokrefbi4jxdomnxslxe
Multiple Receptive Field Network (MRF-Net) for Autonomous Underwater Vehicle Fishing Net Detection Using Forward-Looking Sonar Images
2021
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We trained and tested the network with data collected in the sea using a Gemini 720i multi-beam forward-looking sonar and compared it with state-of-the-art networks for object detection. ...
In this paper, we propose an object detection multiple receptive field network (MRF-Net), which is used to recognize and locate fishing nets using forward-looking sonar (FLS) images. ...
In addition, convolutional neural networks have also been used for detecting objects in FLS images [29] , where a CNN is trained on box proposals generated by a sliding window and screened with intersection ...
doi:10.3390/s21061933
pmid:33801861
fatcat:6rmky3nombe6rjrfrhlcxm3ioq
Deep Learning from Shallow Dives: Sonar Image Generation and Training for Underwater Object Detection
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We validate the proposed scheme by training using a simulator and by testing the simulated images with real underwater sonar images obtained from a water tank and the sea. ...
To tackle this issue, this paper presents a solution to this field's lack of data by introducing a novel end-to-end image-synthesizing method in the training image preparation phase. ...
Differing from those early studies who focused on generation of images, this paper proposes an end-to-end solution to prepare a training dataset for underwater object detection and validating with real ...
arXiv:1810.07990v1
fatcat:y7kp2xumpzabnettkpbmeb53qy
Detecting Submerged Objects Using Active Acoustics and Deep Neural Networks: a Test Case for Pelagic Fish
2021
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
However, training the network directly on the real reflections with data augmentation techniques allowed to reach a more favorable precision-recall trade-off, approaching an ideal detection bound. ...
To allow for real-time detection, we use a convolutional neural network, which provides the simultaneous labeling of a large buffer of signal samples. ...
For example, in [40] retinal color images were synthesized by applying techniques based on adversarial learning, indicating that the resulting images are substantially different from the real ones, but ...
doi:10.5281/zenodo.4983077
fatcat:bcfqvw5v6nc2bp2ddimfb423zu
A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance
2022
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
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 ...
The latter are used for coping with the scarcity of annotated sonar datasets from real maritime missions. ...
Similarly, an autoencoder based on a convolutional neural network was applied to perform sonar image noise reduction [146] , generating a dataset of high-quality sonar images from a single image by applying ...
doi:10.3390/s22062181
pmid:35336352
pmcid:PMC8954367
fatcat:t4ol7zpkbrbujez2teg3vg7sge
Detecting Submerged Objects Using Active Acoustics and Deep Neural Networks: a Test Case for Pelagic Fish
2020
IEEE Transactions on Mobile Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
However, training the network directly on the real reflections with data augmentation techniques allowed to reach a more favorable precision-recall trade-off, approaching an ideal detection bound. ...
To allow for real-time detection, we use a convolutional neural network, which provides the simultaneous labeling of a large buffer of signal samples. ...
For example, in [40] retinal color images were synthesized by applying techniques based on adversarial learning, indicating that the resulting images are substantially different from the real ones, but ...
doi:10.1109/tmc.2020.3044397
fatcat:djjlzpgsfnfflcevcil347pnbu
Improving Automated Sonar Video Analysis to Notify About Jellyfish Blooms
2020
IEEE Sensors Journal
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2103.04068v1 fatcat:g4eijcsf2jhmhauxndu7mfvyba
In this paper, a number of enhancements are proposed to the part of the system that is responsible for object classification. ...
Then, the framework is enhanced by employing a new second stage model, which analyzes the outputs of the first network to make the final prediction. ...
Generative adversarial networks (GANs) [32] have been improving rapidly, and can now produce highly realistic machine generated images [33] , [34] . ...
doi:10.1109/jsen.2020.3032031
fatcat:mehe6tzgj5ccxgelcofozhkd4y
Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition
2021
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct ...
We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for the Diabetic Retinopathy recognition problem, which is considered a state-of-the-art endeavor. ...
Therefore, in this paper, we propose a new Speckle Noise (SN) attack using adversarial image generation, and two defensive methods against these attacks, including defensive adversarial training and feature ...
doi:10.3390/s21113922
fatcat:ctlmaxj45bfdllzxclu7utc5we
A Novel AlphaSRGAN for Underwater Image Super Resolution
2021
Computers Materials & Continua
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
After the images are processed by the generator network, they are passed through an adversarial method for training models. ...
To overcome problems in resolution and to make better use of the Super-Resolution (SR) method, this paper introduces a novel method that has been derived from the Alpha Generative Adversarial Network ( ...
[13] introduced a Generative Adversarial Network method that can give comprehensive information with refined image quality and network stability and be trained in steps. ...
doi:10.32604/cmc.2021.018213
fatcat:5jlxuzefcvestgzhhrkm6zt74y
A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The open question and forward thinking with an envision in 6G wireless networks end the paper. ...
Also, the paper can be considered as a dictionary for experienced researchers to search and find new interesting orientation. ...
Multi-view 3d object detection network for autonomous driving. ...
arXiv:1909.05214v4
fatcat:itnluvkewfd6fel7x65wdgig3e
NUICNet: Non-uniform illumination correction for underwater image using fully convolutional network
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To solve this problem, we propose a non-uniform illumination correction algorithm based on a fully convolutional network for underwater images. ...
To improve the perception ability of the network effectively, the original image and parameters which pre-trained on the ImageNet are concentrated. ...
Moreover, feature loss also combines the features of the pre-trained model on a large dataset (ImageNet) to enhance the generalization of the network, making our model suitable for a variety of scenes ...
doi:10.1109/access.2020.3002593
fatcat:wgntctyhsbeornxuxyjfrth4la
A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images. ...
Our results show that FSL methods offer a significant advantage over the traditional transfer learning methods that fine-tune pre-trained models. ...
ACKNOWLEDGEMENT We want to give a special thanks to Antti Karjalainen for generating the simulated side-scan sonar data. ...
arXiv:2005.04621v2
fatcat:bv4dclxuxvf7bmbkg463aycscu
« Previous
Showing results 1 — 15 out of 303 results