基于Morlet小波Canny边缘检测的遥感视觉提取

Remote Sensing Visual Extraction Based on Morlet Wavelet and Canny Edge Detection

传统的Canny边缘检测方法提取遥感图像边缘视觉特征在设定不变矩阈值采用经验模式,导致视觉提取分辨率不好,特征提取不准。提出采用Morlet小波变换对遥感图像边缘特征进行不变矩阈值函数构建,提出一种基于Morlet小波Canny边缘检测算法的遥感图像视觉特征提取。将图像数据经过Canny边缘检测和标记分水岭分割,实现遥感图像视觉提取。仿真实验表明,该方法在遥感图像视觉特征提取上比传统的Canny边缘检测方法效果明显,提取正确率最高可以达到94.20%,算法将在远距离遥感目标识别和监测等领域具有很好的应用价值。

Traditional Canny edge detection methods for feature extraction of remote sensing image edge vision in the set-ting of moment invariant threshold is taken by using empirical mode, resulting in visual resolution is not good. The remote sensing image edge features are invariant threshold function constructed by Morlet wavelet transform, and we propose a kind of remote sensing image feature visual Morlet wavelet edge detection algorithm based on the extraction of Canny. Re-mote sensing image extraction is obtained. Simulation results show that, the method in remote sensing image visual feature extraction than conventional Canny edge detection methods and obvious effect, extraction accuracy can reach 94.20% of the maximum, the algorithm will have good application value in the field of remote sensing target identification and monitor-ing.