论文部分内容阅读
噪声对遥感图像的后续处理产生负面影响,为了有效消除遥感图像中的噪声,提出一种基于边缘检测的遥感图像去噪方法。首先对含噪的原始遥感图像进行NSCT分解,得到不同尺度和方向的子带图像,然后利用KPCA对分解后的遥感子带图像进行去噪处理,并采用NSCT对遥感子带图像进行重构,最后采用双边滤波器对去噪后的遥感图像边缘进行平滑处理,消除边缘中的奇异噪声点。实验结果证明,本文方法不仅可以有效去除遥感图像中的噪声,可以保留遥感图像的边缘信息,而且获得了比其它方法更优的遥感图像去噪效果。
Noise has a negative impact on the subsequent processing of remote sensing images. In order to effectively eliminate the noise in remote sensing images, a remote sensing image denoising method based on edge detection is proposed. Firstly, the original noisy remote sensing images are decomposed by NSCT to obtain sub-band images with different scales and orientations. Then, the decomposed remote sensing sub-band images are denoised by KPCA, and the remote sensing sub-band images are reconstructed by NSCT. Finally, a bilateral filter is used to smooth the edge of the denoised remote sensing image to eliminate the singular noise point in the edge. Experimental results show that the proposed method can not only effectively remove the noise in remote sensing images, but also preserve the edge information of remote sensing images and obtain better remote sensing image denoising effect than other methods.