空间适应性分割尺度下的海底底质声学图像分类

尚晓东; 董理; 赵建虎; 张志强

doi:10.12382/bgxb.2024.0599

您当前的位置：

首页 >

文章列表页 >

空间适应性分割尺度下的海底底质声学图像分类

更新时间：2025-09-05

- 空间适应性分割尺度下的海底底质声学图像分类
- Classification of Seafloor Sediments Using Acoustic Image Based on Spatially Adaptive Segmentation Scales
- 兵工学报 2025年46卷第5期页码：240599
- 作者机构：
  
  1. 海军工程大学, 湖北武汉 430033
  2. 武汉大学测绘学院, 湖北武汉 430079
- 作者简介：
  
  * 邮箱: 12357609@qq.com
- 基金信息：
  
  国家自然科学基金项目(42176186)
- DOI：10.12382/bgxb.2024.0599
  中图分类号：
- 收稿：2024-07-18，
  
  网络出版：2025-05-07，
  
  纸质出版：2025-05-31
- 稿件说明：
移动端阅览
尚晓东, 董理, 赵建虎, 等. 空间适应性分割尺度下的海底底质声学图像分类[J]. 兵工学报, 2025,46(5):240599.

Xiaodong SHANG, Li DONG, Jianhu ZHAO, et al. Classification of Seafloor Sediments Using Acoustic Image Based on Spatially Adaptive Segmentation Scales[J]. Acta Armamentarii, 2025, 46(5): 240599.
尚晓东, 董理, 赵建虎, 等. 空间适应性分割尺度下的海底底质声学图像分类[J]. 兵工学报, 2025,46(5):240599. DOI： 10.12382/bgxb.2024.0599.

Xiaodong SHANG, Li DONG, Jianhu ZHAO, et al. Classification of Seafloor Sediments Using Acoustic Image Based on Spatially Adaptive Segmentation Scales[J]. Acta Armamentarii, 2025, 46(5): 240599. DOI： 10.12382/bgxb.2024.0599.

摘要

针对目前面向对象的海底声学图像分类中分割尺度的确定存在经验性和受人为因素影响显著等问题

提出一种以混淆指数作为客观指标的空间适应性分割尺度确定方法。通过给定一组分割尺度

计算得到对应的分割对象的回波强度均值和标准差。采用非监督聚类K-means算法

计算不同分割尺度下分类结果的混淆指数

选择最小混淆指数对应的分割尺度作为提取海底图像特征的最优尺度。基于最优分割尺度提取海底图像特征

联合采样数据建立监督分类模型

预测整个测量区域的底质分布结果。研究结果表明

采用空间适应性分割尺度

能够显著提高底质分类的精度。实验采用交叉检验

验证了新方法的有效性

而且针对回波强度特征较为一致的底质

在实验中通过引入地形特征进一步提高了分类精度。

Abstract

At present

the determination of segmentation scale in the object-oriented seafloor acoustic image classification is empirical and significantly influenced by human factors. A spatially adaptive segmentation scale determination method using the confusion index as an objective index is proposed. The mean value and standard deviation of echo intensity corresponding to the segmentation objects are calculated by giving a set of segmentation scales. The unsupervised K-means clustering algorithm is then adopted to calculate the confusion indexes pf classification results at different segmentation scales

and the segmentation scale corresponding to the minimum confusion index is selected as the optimal scale to extract the seafloor image features. Based on the seafloor image features extracted at the optimal scale

a supervised classification model is established by combining the sampled data to predict the distribution of sediments in the whole surveying area. Experimental results prove that the spatially adaptive segmentation scales can be used to improve the classification accuracy significantly. The effectiveness of the proposed method is verified by cross-check in the experiment. Moreover

for thesegments that are with the relatively consistent the echo intensity characteristics

the classification accuracy can be further improved by introducing the terrain features.

关键词

Keywords

references

王沫 , 金绍华 , 王美娜 , 等 . 海底底质测量数据处理技术体系研究 [J ] . 海洋测绘 , 2021 , 41 ( 1 ): 56 - 60 .

WANG M , JIN S H , WANG M N , et al. Research on technical system of seabed sedimen surveying data processing [J ] . Hydroaphic Surveying and Charting , 2021 , 41 ( 1 ): 56 - 60 . (in Chinese)

赵玉新 , 赵廷 . 海底声呐图像智能底质分类技术研究综述 [J ] . 智能系统学报 , 2020 , 15 ( 3 ): 587 - 600 .

ZHAO Y X , ZHAO T . Survey of the intelligent seabed sediment classification technology based on sonar images [J ] . CAAI Transactions on Intelligent Systems , 2020 , 15 ( 3 ): 587 - 600 . (in Chinese)

李通旭 , 张效民 , 韩冲 , 等 . 掩埋水雷在不同海底和掩埋深度的声衰减建模 [J ] . 兵工学报 , 2014 , 35 ( 3 ): 428 - 432 . DOI: 10.3969/j.issn.1000-1093.2014.03.021 http://doi.org/10.3969/j.issn.1000-1093.2014.03.021 采用Biot-Stoll海底模型分别预测了声波在粗沙、沙质泥和粘土质泥3种典型海底的声衰减系数与声透射系数，通过研究多种海底的声传播特性，建立了掩埋条件下水雷在不同海底和不同掩埋深度的声衰减模型，分析了掩埋对水雷声引信性能的影响。研究结果表明：不同的海底底质、不同的掩埋深度和不同的引信工作频段都会在不同程度下影响水雷声引信的工作性能，在相同的掩埋深度下，10 Hz~5 kHz引信频带内，粗沙海底对声引信的影响最大，粘土质泥对声引信的影响最小，随着海底底质平均颗粒直径的减小和孔隙度的增加，掩埋对声引信的影响有逐渐减小的趋势。

LI T X , ZHANG X M , HAN C , et al , Acoustic attenuation modeling of buried mines in different sediments and depths [J ] . Acta Armamentarii , 2014 , 35 ( 3 ): 428 - 432 . (in Chinese)

范超 , 王鼎 , 杨宾 , 等 . 信号传播速度未知下水下多基地声纳定位算法 [J ] . 兵工学报 , 2022 , 43 ( 3 ): 637 - 652 . DOI: 10.12382/bgxb.2021.0134 http://doi.org/10.12382/bgxb.2021.0134 针对水下多基地声纳定位系统中声波信号传播速度未知的情况，以到达时间差为系统观测量，提出一种基于误差约束等式的联合估计声波信号传播速度和目标源位置的闭式解定位算法。算法需要分两步进行。第1步通过引入辅助变量，将非线性观测方程转化为伪线性方程进行处理，求得目标源位置以及信号传播速度的初始估计解；第2步根据初始估计解的估计误差所服从的等式约束，构造新的优化模型，再用拉格朗日乘子法进行求解。推导了算法的联合估计均方误差，从理论上证明了其可以达到相应的克拉美罗界。通过数值仿真验证了估计均方误差的理论分析，并与现有算法进行仿真比较，证明了所提算法与现有算法相比具有优越性。

FAN C , WANG D , YANG B , et al. An algorithm for underwater target localization of multistatic sonar system with unknown signal propagation speed [J ] . Acta Armamentarii , 2022 , 43 ( 3 ): 637 - 652 . (in Chinese) DOI: 10.12382/bgxb.2021.0134 http://doi.org/10.12382/bgxb.2021.0134 For the unknown propagation speed of acoustic signal under water，a closed-form localization algorithm based on error constraint equation is proposed to estimate the acoustic signal propagation speed and target location for underwater multistatic sonar system，in which the time difference of arrival is taken as an observable quantity.The proposed algorithm falls into two steps. In the first step，the nonlinear observation equations are transformed into the pseudo-linear equations by introducing auxiliary variables，and the initial estimation solutions of target location and signal propagation speed are obtained. In the second step，a new optimization model is obtained according to the equality constraint of estimated error of the initial estimation solutions，and the Lagrange multiplier method is used to solve the problem.Then the jointly estimated mean square error of the proposed algorithm is derived. It is theoretically proven that the estimated mean square error can reach the corresponding Cramér-Rao bound. Finally，the theoretical analysis of the estimated mean square error is verified by numerical simulation，and the comparison shows that the proposed algorithm is superior to the existing algorithms.

李官保 , 王景强 , 孟祥梅 , 等 . 中国近海主要表层沉积物类型的原位声学特性 [J ] . 哈尔滨工程大学学报 , 2024 , 45 ( 1 ): 189 - 197 .

LI G B , WANG J Q , MENG X M , et al. In-situ acoustic properties of the main types of sediment in the offshore areas of China [J ] . Journal of Harbin Engineering University , 2024 , 45 ( 1 ): 189 - 197 . (in Chinese)

MISIUK B , BROWN C . Benthic habitat mapping: a review of three decades of mapping biological patterns on the seafloor [J ] . Estuarine, Coastal and Shelf Science , 2024 , 296 : 108599 .

SMITH L , STARK N , JABER R . Relating side scan sonar backscatter data to geotechnical properties for the investigation of surficial seabed sediments [J ] . Geo-Marine Letters , 2023 , 43 ( 2 ): 9 - 18 .

倪海燕 , 王文博 , 任群言 , 等 . 多波束声呐海底底质半监督学习分类方法 [J ] . 声学技术 , 2023 , 42 ( 4 ): 524 - 532 .

NI H Y , WANG W B , REN Q Y , et al. Semi-supervised learning methods for seafloor sediment classification using multi-beam sonar [J ] . Technical Acoustics , 2023 , 42 ( 4 ): 524 - 532 . (in Chinese)

ZHANG Q Y , ZHAO J H , LI S B , et al. Seabed sediment classification Using Spatial Statistical Characteristics [J ] . Journal of Marine Science and Engineering , 2022 , 10 ( 5 ): 691 .

SUMMERS G , AARON L , ANDREW J W . Multi resolution appraisal of Cork Harbour estuary: an object based image analysis approach [J ] . Geomorphology , 2023 ,439: 108851.

DIESING M , MITCHELL P , STEPHENS D . Image-based seabed classification: what can we learn from terrestrial remote sensing? [J ] . ICES Journal of Marine Science , 2016 , 73 ( 10 ): 2425 - 2441 .

MISIUK B , TAN Y L , LI M Z , et al. Multivariate mapping of seabed grain size parameters in the Bay of Fundy using convolutional neural networks [J ] . Marine Geology , 2024 , 472 : 107299 .

KAVZOGLU T , TONBUL H . An experimental comparison of multi-resolution segmentation, SLIC and K-means clustering for object-based classification of VHR imagery [J ] . International Journal of Remote Sensing , 2018 , 39 ( 18 ): 6020 - 6036 .

JANOWSKI L , WROBLEWSKI R , DWORNICZAK J , et al. Offshore benthic habitat mapping based on object-based image analysis and geomorphometric approach. a case study from the Slupsk Bank, Southern Baltic Sea [J ] . Science of The Total Environment , 2021 , 801 : 149712 .

IERODIACONOU D , SCHIMEL A C , KENNEDY D , et al. Combining pixel and object based image analysis of ultra-high resolution multibeam bathymetry and backscatter for habitat mapping in shallow marine waters [J ] . Marine Geophysical Research , 2018 , 39 : 271 - 288 .

SUMMERS G , LIM A , WHELLER A J . A scalable, supervised classification of seabed sediment waves using an object-based image analysis approach [J ] . Remote Sensing , 2021 , 13 ( 12 ): 2317 .

GRIPPA T , LENNERT M , BEAUMONT B , et al. An open-source semi-automated processing chain for urban object-based classification [J ] . Remote Sensing , 2017 , 9 ( 4 ): 358 .

MASETTI G , MAYER L A , WARD L G . A bathymetry-and reflectivity-based approach for seafloor segmentation [J ] . Geosciences , 2018 , 8 ( 1 ): 14 .

ISMAIL K , HUVENNE V , ROBERT K . Quantifying spatial heterogeneity in submarine canyons [J ] . Progress in Oceanography , 2018 , 169 : 181 - 198 .

KUCHARCZYK M , HAY G J , GHAFFARIAN S , et al. Geographic object-based image analysis: a primer and future directions [J ] . Remote Sensing , 2020 , 12 ( 12 ): 2012 .

ANDERS N S , SEIJMONSBERGEN A C , BOUTEN W . Segmentation optimization and stratified object-based analysis for semi-automated geomorphological mapping [J ] . Remote Sensing of Environment , 2011 , 115 ( 12 ): 2976 - 2985 .

SHANG X D , DONG L , ZHAO J H . Optimal scale determination for object-based backscatter image analysis in seafloor substrate classification based on classification uncertainty [J ] . IEEE Geoscience and Remote Sensing Letters , 2024 ,21: 1501005.

杨涛涛 , 吕福亮 , 鲁银涛 , 等 . 南海西沙海域多种海底地貌特征及成因 [J ] . 海相油气地质 , 2021 , 26 ( 4 ): 307 - 318 .

YANG T T , LÜ F L , LU Y T , et al. Characteristics and genesis of various seafloor topography in Xisha sea area,South China Sea [J ] . Marine Origin Petroleum Geology , 2021 , 26 ( 4 ): 307 - 318 . (in Chinese)

LI S B , SHANG X D , WANG S Q , et al. A geometric and radiometric-invariant matching method for SSS and MBES data [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 , 62 : 1 - 13 .

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据