论文部分内容阅读
船舶分类与识别对于海洋交通运输监测与管理具有重要意义,同时也是SAR海洋应用的重要组成部分。COSMO-SkyMed高分辨率合成孔径雷达(SAR)图像下,商用船舶的结构轮廓明显,散货船、集装箱船和油船的特征清晰可辨,为船舶识别分类提供有效支持。提出了一种基于结构特征分析的商用船舶分类算法,通过提取核密度估计值、船舶积分主轴位置及左中右3部分积分量比例等特征,可实现船舶类型的区分。通过在东海试验区的同步实验,证明COSMO-SkyMed图像商用船舶分类算法的平均分类精度达到89.94%。
Classification and identification of ships is of great significance to the monitoring and management of maritime traffic and transportation, and is also an important part of SAR marine applications. Under the COSMO-SkyMed high-resolution SAR image, the structural profile of commercial vessels is clear, and the features of bulk carriers, container ships and oil tankers are clearly distinguishable, providing effective support for classification and identification of ships. A commercial ship classification algorithm based on structural feature analysis is proposed. The classification of ship types can be achieved by extracting features such as nuclear density estimation, ship integral principal axis position, and left-middle-right integral proportion. Through the synchronization experiments in the East China Sea experimental area, the average classification accuracy of COSMO-SkyMed commercial ship classification algorithm is 89.94%.