Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning
There are many challenges in using side-scan sonar (SSS) images to detect objects. The challenge of object detection and recognition in sonar data is greater than in optical images due to the sparsity of detectable targets. The complexity of real-world underwater scanning presents additional difficu...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/12/2/352 |
_version_ | 1797297744694476800 |
---|---|
author | Jier Xi Xiufen Ye |
author_facet | Jier Xi Xiufen Ye |
author_sort | Jier Xi |
collection | DOAJ |
description | There are many challenges in using side-scan sonar (SSS) images to detect objects. The challenge of object detection and recognition in sonar data is greater than in optical images due to the sparsity of detectable targets. The complexity of real-world underwater scanning presents additional difficulties, as different angles produce sonar images of varying characteristics. This heterogeneity makes it difficult for algorithms to accurately identify and detect sonar objects. To solve these problems, this paper presents a novel method for sonar image target detection based on a transformer and YOLOv7. Thus, two data augmentation techniques are introduced to improve the performance of the detection system. The first technique applies stain-like noise to the training optical image data to simulate the real sonar image environment. The second technique adds multiple shadows to the optical image and 3D data targets to represent the direction of the target in the sonar image. The proposed method is evaluated on a public sonar image dataset, and the experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and speed. The experimental results show that our method achieves better precision. |
first_indexed | 2024-03-07T22:25:47Z |
format | Article |
id | doaj.art-79339faf42224f3f8163c37dfa0c173f |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-07T22:25:47Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-79339faf42224f3f8163c37dfa0c173f2024-02-23T15:23:22ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-02-0112235210.3390/jmse12020352Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot LearningJier Xi0Xiufen Ye1College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaThere are many challenges in using side-scan sonar (SSS) images to detect objects. The challenge of object detection and recognition in sonar data is greater than in optical images due to the sparsity of detectable targets. The complexity of real-world underwater scanning presents additional difficulties, as different angles produce sonar images of varying characteristics. This heterogeneity makes it difficult for algorithms to accurately identify and detect sonar objects. To solve these problems, this paper presents a novel method for sonar image target detection based on a transformer and YOLOv7. Thus, two data augmentation techniques are introduced to improve the performance of the detection system. The first technique applies stain-like noise to the training optical image data to simulate the real sonar image environment. The second technique adds multiple shadows to the optical image and 3D data targets to represent the direction of the target in the sonar image. The proposed method is evaluated on a public sonar image dataset, and the experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and speed. The experimental results show that our method achieves better precision.https://www.mdpi.com/2077-1312/12/2/352sonar imagetransformerstain-like noisemultiple shadows |
spellingShingle | Jier Xi Xiufen Ye Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning Journal of Marine Science and Engineering sonar image transformer stain-like noise multiple shadows |
title | Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning |
title_full | Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning |
title_fullStr | Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning |
title_full_unstemmed | Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning |
title_short | Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning |
title_sort | sonar image target detection based on simulated stain like noise and shadow enhancement in optical images under zero shot learning |
topic | sonar image transformer stain-like noise multiple shadows |
url | https://www.mdpi.com/2077-1312/12/2/352 |
work_keys_str_mv | AT jierxi sonarimagetargetdetectionbasedonsimulatedstainlikenoiseandshadowenhancementinopticalimagesunderzeroshotlearning AT xiufenye sonarimagetargetdetectionbasedonsimulatedstainlikenoiseandshadowenhancementinopticalimagesunderzeroshotlearning |