A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images

Underwater object detection with Synthetic Aperture Sonar (SAS) images faces many problems, including low contrast, blurred edges, high-frequency noise, and missed small objects. To improve these problems, this paper proposes a high-accuracy underwater object detection algorithm for SAS images, name...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiahui Su, Deyin Xu, Lu Qiu, Zhiping Xu, Lixiong Lin, Jiachun Zheng
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2112
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704294392004608
author Jiahui Su
Deyin Xu
Lu Qiu
Zhiping Xu
Lixiong Lin
Jiachun Zheng
author_facet Jiahui Su
Deyin Xu
Lu Qiu
Zhiping Xu
Lixiong Lin
Jiachun Zheng
author_sort Jiahui Su
collection DOAJ
description Underwater object detection with Synthetic Aperture Sonar (SAS) images faces many problems, including low contrast, blurred edges, high-frequency noise, and missed small objects. To improve these problems, this paper proposes a high-accuracy underwater object detection algorithm for SAS images, named the HAUOD algorithm. First, considering SAS image characteristics, a sonar preprocessing module is designed to enhance the signal-to-noise ratio of object features. This module incorporates three-stage processing for image quality optimization, and the three stages include collaborative adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement, non-local mean denoising, and frequency-domain band-pass filtering. Subsequently, a novel C2fD module is introduced to replace the original C2f module to strengthen perception capabilities for low-contrast objects and edge-blurred regions. The proposed C2fD module integrates spatial differential feature extraction, dynamic feature fusion, and Enhanced Efficient Channel Attention (Enhanced ECA). Furthermore, an underwater multi-scale contextual attention mechanism, named UWA, is introduced to enhance the model’s discriminative ability for multi-scale objects and complex backgrounds. The proposed UWA module combines noise suppression, hierarchical dilated convolution groups, and dual-dimensional attention collaboration. Experiments on the Sonar Common object Detection dataset (SCTD) demonstrate that the proposed HAUOD algorithm achieves superior performance in small object detection accuracy and multi-scenario robustness, attaining a detection accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.1</mn><mo>%</mo></mrow></semantics></math></inline-formula>, which is <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>8.3</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher than the baseline model (YOLOv8n). Compared with YOLOv8s, the proposed HAUOD algorithm can achieve <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>6.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher accuracy with only <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>50.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> model size, and reduce the computational complexity by half. Moreover, the HAUOD method exhibits significant advantages in balancing computational efficiency and accuracy compared to mainstream detection models.
format Article
id doaj-art-b211998ecef74164b0884bd64b35ed41
institution DOAJ
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-b211998ecef74164b0884bd64b35ed412025-08-20T03:16:47ZengMDPI AGRemote Sensing2072-42922025-06-011713211210.3390/rs17132112A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar ImagesJiahui Su0Deyin Xu1Lu Qiu2Zhiping Xu3Lixiong Lin4Jiachun Zheng5School of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen 361021, ChinaUnderwater object detection with Synthetic Aperture Sonar (SAS) images faces many problems, including low contrast, blurred edges, high-frequency noise, and missed small objects. To improve these problems, this paper proposes a high-accuracy underwater object detection algorithm for SAS images, named the HAUOD algorithm. First, considering SAS image characteristics, a sonar preprocessing module is designed to enhance the signal-to-noise ratio of object features. This module incorporates three-stage processing for image quality optimization, and the three stages include collaborative adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement, non-local mean denoising, and frequency-domain band-pass filtering. Subsequently, a novel C2fD module is introduced to replace the original C2f module to strengthen perception capabilities for low-contrast objects and edge-blurred regions. The proposed C2fD module integrates spatial differential feature extraction, dynamic feature fusion, and Enhanced Efficient Channel Attention (Enhanced ECA). Furthermore, an underwater multi-scale contextual attention mechanism, named UWA, is introduced to enhance the model’s discriminative ability for multi-scale objects and complex backgrounds. The proposed UWA module combines noise suppression, hierarchical dilated convolution groups, and dual-dimensional attention collaboration. Experiments on the Sonar Common object Detection dataset (SCTD) demonstrate that the proposed HAUOD algorithm achieves superior performance in small object detection accuracy and multi-scenario robustness, attaining a detection accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.1</mn><mo>%</mo></mrow></semantics></math></inline-formula>, which is <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>8.3</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher than the baseline model (YOLOv8n). Compared with YOLOv8s, the proposed HAUOD algorithm can achieve <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>6.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher accuracy with only <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>50.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> model size, and reduce the computational complexity by half. Moreover, the HAUOD method exhibits significant advantages in balancing computational efficiency and accuracy compared to mainstream detection models.https://www.mdpi.com/2072-4292/17/13/2112synthetic aperture sonarunderwater object detectionunderwater image preprocessingfeature fusion
spellingShingle Jiahui Su
Deyin Xu
Lu Qiu
Zhiping Xu
Lixiong Lin
Jiachun Zheng
A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images
Remote Sensing
synthetic aperture sonar
underwater object detection
underwater image preprocessing
feature fusion
title A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images
title_full A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images
title_fullStr A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images
title_full_unstemmed A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images
title_short A High-Accuracy Underwater Object Detection Algorithm for Synthetic Aperture Sonar Images
title_sort high accuracy underwater object detection algorithm for synthetic aperture sonar images
topic synthetic aperture sonar
underwater object detection
underwater image preprocessing
feature fusion
url https://www.mdpi.com/2072-4292/17/13/2112
work_keys_str_mv AT jiahuisu ahighaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT deyinxu ahighaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT luqiu ahighaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT zhipingxu ahighaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT lixionglin ahighaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT jiachunzheng ahighaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT jiahuisu highaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT deyinxu highaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT luqiu highaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT zhipingxu highaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT lixionglin highaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages
AT jiachunzheng highaccuracyunderwaterobjectdetectionalgorithmforsyntheticaperturesonarimages