Automatic Tracking Sea Bottom Line on Side-Scan Sonar Image by Direction Adaptive DBSCAN

WANG Aixue; JIN Shaohua; LIU Tianyang; ZHA Wenfu; LIU Chang

doi:10.13203/j.whugis20220733

您当前的位置：

首页 >

文章列表页 >

Automatic Tracking Sea Bottom Line on Side-Scan Sonar Image by Direction Adaptive DBSCAN

Geodesy and Survey Engineering | 更新时间：2026-11-05

- Automatic Tracking Sea Bottom Line on Side-Scan Sonar Image by Direction Adaptive DBSCAN
- Geomatics and Information Science of Wuhan University Vol. 50, Issue 4, Pages: 674-683(2025)
- 作者机构：
  
  1.武汉大学测绘学院，湖北武汉，430079
  2.海军大连舰艇学院海洋测绘工程军队重点实验室，辽宁大连，116018
  3.武汉长江航道救助打捞局，湖北武汉，430014
- 作者简介：
- 基金信息：
- DOI：10.13203/j.whugis20220733
  CLC： P229
- Received：18 January 2023，
  
  Published：05 April 2025
- 稿件说明：
移动端阅览
王爱学,金绍华,刘天阳，等.采用方向自适应密度聚类自动检测侧扫声呐图像海底线[J].武汉大学学报（信息科学版）,2025,50(4):674-683.

WANG Aixue,JIN Shaohua,LIU Tianyang,et al.Automatic Tracking Sea Bottom Line on Side-Scan Sonar Image by Direction Adaptive DBSCAN[J].Geomatics and Information Science of Wuhan University,2025,50(4):674-683.
王爱学,金绍华,刘天阳，等.采用方向自适应密度聚类自动检测侧扫声呐图像海底线[J].武汉大学学报（信息科学版）,2025,50(4):674-683. DOI：,10.13203/j.whugis20220733

WANG Aixue,JIN Shaohua,LIU Tianyang,et al.Automatic Tracking Sea Bottom Line on Side-Scan Sonar Image by Direction Adaptive DBSCAN[J].Geomatics and Information Science of Wuhan University,2025,50(4):674-683. DOI：,10.13203/j.whugis20220733

摘要

侧扫声呐是获取海底地貌图像的主要手段之一，海底线是侧扫声呐瀑布图像最显著的特征，准确检测和跟踪海底线是侧扫声呐数据精细处理的基础。受水体环境噪声、船体、水面及水体悬浮目标散射等干扰，传统阈值法及相关图像特征检测算法难以实现海底线自动、准确、高效提取。充分考虑侧扫声呐海底线的边缘特性及沿航迹向密集分布的空间特点，提出了一种边缘方向适应性密度聚类和聚类链筛选相结合的海底线检测方法。该方法通过高斯一阶导卷积模板及非极大值抑制实现高噪声图像边缘梯度和方向计算以及边缘特征的细化；通过设置窄带状搜索邻域，并依据边缘梯度方向实时调整搜索邻域的长轴，以实现对方向变化的线状特征的密度聚类；通过构建基于边缘特征密度聚类的海底线检测策略，包括设定经验范围、阈值法构建聚类种子集、长链原则、排他原则、对称原则、趋势延伸原则、修复原则等，以实现海底线边缘特征的快速密度聚类成链和海底线的筛选。实验验证和对比分析的结果表明，在持续噪声、复杂悬浮物等常见水体回波干扰下，所提方法在海底线检测的准确性和稳定性上优于传统阈值方法，且单呯平均检测耗时仅为0.661 ms。所提侧扫声呐图像海底线检测方法有较好的稳定性和干扰普适性，可在侧扫声呐数据采集和事后处理中推广应用。

Abstract

Objectives

Side scan sonar is one of the main means to acquire the submarine geomorphology image. Sea bottom line is the most prominent feature of the side scan sonar waterfall image. Accurate detection and tracking of the bottom line is the basis of the fine processing of the side scan sonar data.

Methods

Traditional threshold methods and related image feature detection algorithm are difficult to achieve automatic

accurate

and efficient extraction of the sea bottom line due to the interference of water environment noise and scattering sound from the hull

water surface

and other suspended objects in the water. We fully consider the image edge feature of the sea bottom line and its spatial characteristics that distribute along the track line

thus forming a kind of sea bottom line tracking method with the combining of adaptive edge direction density-based spatial clustering and clustering chain screening. The main work includes three parts: First

image edge gradient and direction are calculated through the Gaussian first-order derivative convolution template

edge features are refined by non-maximum suppression. Second

the density-based spatial clustering algorithm is improved with searching direction adaptively by setting the narrow band-shaped search neighborhood and dynamically adjusting the long axis of the search neighborhood based on the direction of the edge gradient. Third

a serial of sea bottom line tracking strategy based on the clustered edge chains set is constructed

which includes setting experience range

constructing the clustering seed set by threshold method

the long chain principle

the exclusion principle

the symmetry principle

the trend extension principle

the repair principle

etc.

Results

Through experimental verification and comparative analysis

the results show that the accuracy and stability of the proposed method are superior to the traditional threshold method

even in the case of common water echo interference such as continuous noise and complex suspended objects

the average single ping detection time is only 0.661 ms.

Conclusions

The sea-bottom line detection method of side-scan sonar image has good stability and anti-interference performance

and has great potential to be a generalized method for onboard data acquisition and post-processing of side-scan sonar.

关键词

Keywords

references

BLONDEL P . The Handbook of Sidescan Sonar ［M］. Berlin ： Springer Science & Business Media .

CHAVEZ P S ， ISBRECHT J ， GALANIS P ， et al . Processing， Mosaicking and Management of the Monterey Bay Digital Sidescan-Sonar Images ［J］. Marine Geology ， 2002 ， 181 （ 1-3 ）： 305 - 315 .

LURTON X ， JACKSON D R . An Introduction to Underwater Acoustics ［J］. The Journal of the Acoustical Society of America ， 2004 ， 115 （ 2 ）： 443 .

CHI C . Basic Theory for Underwater Real-Time 3-D Acoustical Imaging： Theory， Algorithm and System Design ［J］. Underwater Real-Time 3D Acoustical Imaging： Theory， Algorithm and System Design ， 2019 ： 11 - 19 .

ZHAO J H ， WANG X ， ZHANG H M ， et al . A Comprehensive Bottom-Tracking Method for Sidescan Sonar Image Influenced by Complicated Measuring Environment ［J］. IEEE Journal of Oceanic Engineering ， 2017 ， 42 （ 3 ）： 619 - 631 .

Chesapeake Technology Inc . SonarWiz User Guide ［R］. CA， USA ： Chesapeake Technology Inc ， 2022 .

Triton Imaging Inc . eXtended Triton Formate（XTF）X41 ［S］. CA，USA ： Triton Imaging Inc ， 2016 .

黄攀，唐劲松，钟何平 . 干涉合成孔径声呐复图像配准分段曲面拟合法［J］. 武汉大学学报（信息科学版）， 2021 ， 46 （ 8 ）： 1259 - 1264 .

HUANG Pan ， TANG Jinsong ， ZHONG Heping . Piecewise Surface Fitting Method for Complex Image Registration of Interferometric Synthetic Aperture Sonar ［J］. Geomatics and Information Science of Wuhan University ， 2021 ， 46 （ 8 ）： 1259 - 1264 .

赵建虎，王晓，张红梅 . 侧扫声呐图像海底线自动提取方法研究［J］. 武汉大学学报（信息科学版）， 2017 ， 42 （ 12 ）： 1797 - 1803 .

ZHAO Jianhu ， WANG Xiao ， ZHANG Hongmei . An Automatic Bottom Extracting Method for Side-Scan Sonar Image ［J］. Geomatics and Information Science of Wuhan University ， 2017 ， 42 （ 12 ）： 1797 - 1803 .

SHIH C C ， HORNG M F ， TSENG Y R ， et al . An Adaptive Bottom Tracking Algorithm for Side-Scan Sonar Seabed Mapping ［C］//IEEE Underwater Technology， Kaohsiung， Taiwan， China ， 2019 .

Qi B ， Li X ， Zhang H ， et al . A Real-Time Adaptive Bottom Tracking Method for Bathymetric Side-Scan Sonar ［J］. Proc Romanian Acad A：Math Phys Tech Sci Inf Sci ， 2021 ， 22 （ 1 ）： 63 - 72 .

ZHENG G ， ZHANG H M ， LI Y Q ， et al . A Universal Automatic Bottom Tracking Method of Side Scan Sonar Data Based on Semantic Segmentation ［J］. Remote Sensing ， 2021 ， 13 ： 1945 .

YAN J ， MENG J X ， ZHAO J H . Real-Time Bottom Tracking Using Side Scan Sonar Data Through One-Dimensional Convolutional Neural Networks ［J］. Remote Sensing ， 2020 ， 12 （ 1 ）： 37 .

WANG S P ， LI H T ， LI X Y ， et al . Bottom Tracking Method Based on LOG/Canny and the Threshold Method for Side-Scan Sonar ［J］. Journal of Engineering Science and Technology Review ， 2019 ， 12 （ 6 ）： 134 - 141 .

张济博，潘国富，丁维凤 . 基于LOG算子的侧扫声呐海底线检测［J］. 海洋通报， 2010 ， 29 （ 3 ）： 324 - 328 .

ZHANG Jibo ， PAN Guofu ， DING Weifeng . Bottom Track Method in Sidescan Sonar Data Processing Based on LOG Operator ［J］. Marine Science Bulletin ， 2010 ， 29 （ 3 ）： 324 - 328 .

王杰英 . 侧扫声呐图像的三维重构［D］. 杭州：浙江大学， 2018 .

WANG Jieying . Three-Dimensional Reconstruction of Side Scan Sonar Images ［D］. Hangzhou ： Zhejiang University ， 2018 .

WANG A X ， CHURCH I ， GOU J ， et al . Sea Bottom Line Tracking in Side-Scan Sonar Image Through the Combination of Points Density Clustering and Chains Seeking ［J］. Journal of Marine Science and Technology ， 2020 ， 25 （ 3 ）： 849 - 865 .

EKSTROM M P . Digital Image Processing Techniques ［M］. Cambridge ： Academic Press ， 2012 .

ANSARI M A ， KURCHANIYA D ， DIXIT M . A Comprehensive Analysis of Image Edge Detection Techniques ［J］. International Journal of Multimedia and Ubiquitous Engineering ， 2017 ， 12 （ 11 ）： 1 - 12 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An Improved YOLOv5 Method for Shipwreck Target Detection by Side-Scan Sonar Images

Intelligent Change Detection Method and Application Based on Wuhan-1 Satellite Imagery

Spatiotemporal Intelligence： Theory and Applications

Research Progress in Spatiotemporal Modeling， Analysis， and Prediction of Urban Activity Flows in Built Environment

High-Resolution L-Band InSAR Study of Intense Near-Field Deformation Associated with Shallow Moderate Earthquakes

Related Author

TANG Yulin

BIAN Shaofeng

ZHAI Guojun

LIU Min

ZHANG Weidong

Related Institution

College of Electrical Engineering, Naval University of Engineering

Troops, Hulu Peninsula

Naval Institute of Oceangraphic Surveying and Mapping

Troops

AI问答

⁰