Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis
Side-scan sonar (SSS) images are difficult for automatic analysis due to the acoustic measurement parameters as well as the number of different objects that can be distant. In addition, there is a risk that the seabed analysis application may be attacked. For this purpose, we propose a solution base...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10184003/ |
| _version_ | 1797774908237807616 |
|---|---|
| author | Dawid Polap Antoni Jaszcz Natalia Wawrzyniak Grzegorz Zaniewicz |
| author_facet | Dawid Polap Antoni Jaszcz Natalia Wawrzyniak Grzegorz Zaniewicz |
| author_sort | Dawid Polap |
| collection | DOAJ |
| description | Side-scan sonar (SSS) images are difficult for automatic analysis due to the acoustic measurement parameters as well as the number of different objects that can be distant. In addition, there is a risk that the seabed analysis application may be attacked. For this purpose, we propose a solution based on convolutional neural networks with bilinear pooling in order to achieve higher values of classification accuracy. Bilinear pooling merge data from two networks and return classification results. The first network’s branch receives the original image and the second one after applying the superpixel method. This approach allows to focus on different types of features. In addition, we introduced a mechanism of poisoning detection that analyze images and results from the network. For the evaluation process, we used the real SSS images obtained between two water channels in Szczecin city in north-western Poland. The importance of scientific research indicates the accuracy of the analysis as well as the safety of the measurements performed. |
| first_indexed | 2024-03-12T22:28:00Z |
| format | Article |
| id | doaj.art-c840eaf6992e445a823692fc44b2504d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T22:28:00Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c840eaf6992e445a823692fc44b2504d2023-07-21T23:00:17ZengIEEEIEEE Access2169-35362023-01-0111724777248410.1109/ACCESS.2023.329569310184003Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data AnalysisDawid Polap0https://orcid.org/0000-0003-1972-5979Antoni Jaszcz1https://orcid.org/0000-0002-8997-0331Natalia Wawrzyniak2https://orcid.org/0000-0002-4429-7163Grzegorz Zaniewicz3Faculty of Applied Mathematics, Silesian University of Technology, Gliwice, PolandFaculty of Applied Mathematics, Silesian University of Technology, Gliwice, PolandFaculty of Navigation, Maritime University of Szczecin, Szczecin, PolandFaculty of Navigation, Maritime University of Szczecin, Szczecin, PolandSide-scan sonar (SSS) images are difficult for automatic analysis due to the acoustic measurement parameters as well as the number of different objects that can be distant. In addition, there is a risk that the seabed analysis application may be attacked. For this purpose, we propose a solution based on convolutional neural networks with bilinear pooling in order to achieve higher values of classification accuracy. Bilinear pooling merge data from two networks and return classification results. The first network’s branch receives the original image and the second one after applying the superpixel method. This approach allows to focus on different types of features. In addition, we introduced a mechanism of poisoning detection that analyze images and results from the network. For the evaluation process, we used the real SSS images obtained between two water channels in Szczecin city in north-western Poland. The importance of scientific research indicates the accuracy of the analysis as well as the safety of the measurements performed.https://ieeexplore.ieee.org/document/10184003/Classificationconvolutional neural networksmachine learningpoisoning detectionside-scan sonar images |
| spellingShingle | Dawid Polap Antoni Jaszcz Natalia Wawrzyniak Grzegorz Zaniewicz Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis IEEE Access Classification convolutional neural networks machine learning poisoning detection side-scan sonar images |
| title | Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis |
| title_full | Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis |
| title_fullStr | Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis |
| title_full_unstemmed | Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis |
| title_short | Bilinear Pooling With Poisoning Detection Module for Automatic Side Scan Sonar Data Analysis |
| title_sort | bilinear pooling with poisoning detection module for automatic side scan sonar data analysis |
| topic | Classification convolutional neural networks machine learning poisoning detection side-scan sonar images |
| url | https://ieeexplore.ieee.org/document/10184003/ |
| work_keys_str_mv | AT dawidpolap bilinearpoolingwithpoisoningdetectionmoduleforautomaticsidescansonardataanalysis AT antonijaszcz bilinearpoolingwithpoisoningdetectionmoduleforautomaticsidescansonardataanalysis AT nataliawawrzyniak bilinearpoolingwithpoisoningdetectionmoduleforautomaticsidescansonardataanalysis AT grzegorzzaniewicz bilinearpoolingwithpoisoningdetectionmoduleforautomaticsidescansonardataanalysis |