基于流变特性与纹理特征的底质层界智能识别  

Intelligent Identification of Substrate Boundary Based on Rheological Properties and Texture Characteristics

作　　者：孟皓凡 蒋廷臣 杨志翔 张俊杰 杨雯彦 王圣 MENG Haofan;JIANG Tingchen;YANG Zhixiang;ZHANG Junjie;YANG Wenyan;WANG Sheng(School of Geomatics and Marine Information,Jiangsu Ocean University,Lianyungang 222005,China)

机构地区：[1]江苏海洋大学测绘与海洋信息学院,江苏连云港222005

出　　处：《海洋测绘》2020年第2期27-32,共6页Hydrographic Surveying and Charting

基　　金：国家科技重大专项(2016YFB0501501);国家自然科学基金(41004003);江苏省科技厅项目(BE2016701);连云港市科技项目(SH1506;SH1608;JC1604);江苏省研究生教育教学改革课题(JGZZ16_092);江苏省六大高峰人才项目(JNHB016);江苏省高校优势学科建设工程项目;江苏省品牌专业建设项目;江苏省研究生科研与实践创新计划(SJCX19_0965)

摘　　要：针对传统的人工识别浅剖图像层界方法精度不足、效率低下的问题,提出了一种基于浮泥流变特性与灰度共生矩阵的航道底质层界智能识别方法。利用航道浅剖数据计算灰度共生矩阵特征值来描述底质层界纹理,粗略提取层界边缘;通过浮泥流变特性模型智能识别、连接同一层层界矢量点,准确识别底质层界。对比智能和人工提取连云港航道浅剖数据层界实验的结果表明:结合浮泥流变特性与灰度共生矩阵算法的层界识别方法,可以准确描述底质分布情况,快速自动识别层界线,智能化提取航道底质层界。In order to solve the problems of low accuracy and low efficiency of traditional manual identification method for sub-bottom profiler images,an itelligent idenification method for channel bottom layer boundary based on floating mud rheological properties and gray co-occurrence matrix is proposed.Sub-bottom profiler data is used to calculate gray level co-occurrence matrix eigenvalues,describe the bottom layer of texture,and roughly extract the edge of the boundary layer;Through the model of rheological properties of floating mud,the boundary vector points of the same layer can be identified accurately.The experimental results of intelligent and manual extraction of data layer boundary of lianyungang channel's sub-bottom profiler data show that:the layer boundary recognition method combined with the theological properties of floating mud and the gray-level Co-occurrence matrix algorithm can accurately describe the distribution of sediment,quickly and automatically identifty the layer boundary,and itelligently extract the channel bottom layer boundary.

关 键 词：浅地层剖面仪 底质层界 灰度共生矩阵 流变特性 智能识别 

分 类 号：P229.3[天文地球—大地测量学与测量工程]