基于连通区域提取的中尺度涡自动检测方法研究

Research on Mesoscale Vortex Automatic Detection Based on Connected Region Extraction

论文根据海洋中尺度涡成像的特点,基于边缘检测,运用连通区域提取技术,综合利用涡旋的形状、尺度等判据,设计了一套中尺度涡自动检测算法。该方法主要分为三个步骤:首先对遥感图像数据预处理,包括图像压缩、图像定标、图像边缘检测;然后对图像进行连通区域提取,计算其特征参数;最后对这些连通区域判别检测,提取中尺度涡。研究中使用的决策参数是进行多组数据实验后提取的特征值,随着实验数据的越来越多,特征值也将越来越成熟。论文采用高分三号卫星海洋遥感图像数据进行算法的测试,实验表明该方法可以有效地对遥感图像进行中尺度涡检测。

In this paper,according to the characteristics of the marine mesoscale vortex remote images,a mesoscale vortex automatic detection algorithm is designed.It combines edge detection,the connected region extraction technology,and comprehensive utilization of the shape of vortex,such as scale criterion.This method is mainly divided into three steps:First,remote sensing image data is pretreated by image compression,image scaling and image edge detection.Next,the connected regions are extracted and the characteristic parameters are calculated.Finally,the mesoscale vortices are extracted based on connected component discriminate.The decision-making parameters are extracted eigenvalues based on the study on multiple sets of data in experiments.The characteristic values will become more mature with the increasing number of experimental data.In this paper,the algorithm is tested based on GF-3 marine remote sensing images.The experiment results show that this method can effectively detect mesoscale vortices in remote sensing images.