相位信息遥感图像边缘检测方法的实例检测分析  

Case Detection and Analysis of Phase Information Remote Sensing Image Edge Detection

作　　者：张雪侠[1] 

机构地区：[1]陕西国际商贸学院,陕西西安712046

出　　处：《中国锰业》2018年第1期44-47,共4页China Manganese Industry

摘　　要：边缘作为高分辨率遥感图像分析的重要特征,主要用于定义高分辨率遥感图像中不同地面物体之间的边界。边缘检测作为遥感图像处理中最为重要的手段,业界已经出了许多的边缘检测方法,但在实际检测过程中面对复杂的高分辨率遥感图像,提取其边缘特征往往是较为困难的。针对该问题提出了一种利用相位信息的高分辨率遥感图像边缘检测方法,通过对遥感图像进行傅里叶变换,利用FFT得到幅度谱图;然后对频谱图像采用半径采样和角度采样进行分析,并且根据分析结果设计了二维对数Gaber滤波器;最后将傅里叶变换的结果与滤波器之间的点积进行傅立叶逆变换,从而得到遥感图像的最终检测结果,结果证明该方法较好的对高分辨率遥感图像进行了边缘特征的检测。As an important feature of high resolution remote sensing image analysis,the edge is mainly used to define the boundary between different ground objects in high resolution remote sensing images. Edge Detection is used as the most important means of remote sensing image processing. Many edge detection methods have been developed in the industry. However,it is often difficult to extract the edge features of complex high resolution remote sensing images during the actual detection process. In this paper,we propose a high-resolution remote sensing image edge detection method based on phase information. Fourier transform of remote sensing image is used to obtain the amplitude spectrum by FFT. Then the spectral image is analyzed by radius sampling and angle sampling,And 2D logarithm Gaber filter is designed according to the result of the analysis. Finally,the result of Fourier transform and the dot product of the filter are of inverse Fourier transformed to obtain the final detection result of the remote sensing image. The result shows that this method is better to detect the edge features of high resolution remote sensing images.

关 键 词：高分辨率遥感图像 边缘检测 相位信息 傅里叶变换 图像采样 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]