基于融合技术的遥感图像边缘检测算法

Edge detection algorithm of remote sensing image based on fusion technology

为准确提取遥感图像边缘,研究一种基于融合技术的遥感图像边缘检测算法,考虑到遥感图像中存在乘性噪声,该算法基于自适应滤波器的遥感图像去噪算法,通过自适应滤波器有效去除遥感图像中噪声点;对去噪后的遥感图像,再基于融合技术的遥感图像边缘检测算法,通过滑动窗口技术、模糊增强方法增强去噪后遥感图像边缘,采用模糊形态学算法检测遥感图像边缘。实验结果显示,所提算法去噪后的遥感图像信噪比、峰值信噪比较高,去噪效果极好;边缘检测结果与遥感图像实际边缘位置之间误差较小,检测精度较高,且遥感图像数量的增多,对该算法的检测速度不存在显著的负面影响。

In order to accurately extract the edge of remote sensing image,a remote sensing image edge detection algorithm based on fusion technology is studied.Considering the multiplicative noise in remote sensing image,the algorithm firstly uses the remote sensing image denoising algorithm based on adaptive filter,and effectively removes noise points in remote sensing image through adaptive filter.For the denoised remote sensing image,the remote sensing image edge detection algorithm based on fusion technology is used,the edge of the denoised remote sensing image is enhanced by sliding window technology and fuzzy enhancement method,and the edge of the remote sensing image is detected by fuzzy morphological algorithm.The experimental results show that the SNR and peak SNR of the remote sensing image denoised by the proposed algorithm are high,and the denoising effect is excellent.The error between the edge detection result and the actual edge position of the remote sensing image is small,the detection accuracy is high,and the increase of the number of remote sensing images has no significant negative impact on the detection speed of the algorithm.