基于SOFM网络的声图非监督分类  

Sonar Image Clustering Analysis by SOFM

作　　者：曾旭平[1] 阳凡林[2] 李陶[3] 赵建虎[3] 

机构地区：[1]中交公路规划设计院 [2]山东科技大学地球信息科学与工程学院,泰安市岱宗大街223号271019 [3]武汉大学测绘学院,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2004年第11期977-980,共4页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目 ( 4 0 0 0 40 0 1)

摘　　要：利用局部窗口内的灰度纹理共生矩阵的统计量、灰度均值和两个分维数作为特征矢量 ,利用SOFM网络进行非监督分类侧扫声纳海底图像 ,通过实测数据验算 。Seabed image is clustered according to SOFM network. The feature vectors are average intensity, six statistics of texture and two dimensions of fractal. It takes the spatial correlation between different pixels and the terrain coarseness into consideration. Double blanket algorithm is used to calculate dimension. Because a uniform fractal may not be sufficient to describe a seafloor, two dimensions are calculated, respectively, by the upper blanket and the lower blanket. Dimensions are different in across-track and along-track, so the average of four directions is used to solve this problem.

关 键 词：侧扫声纳 SOFM网络 共生矩阵 分形 分类 

分 类 号：P229[天文地球—大地测量学与测量工程] P237.4[天文地球—测绘科学与技术]