一种新型隧道图像去噪方法——基于小波变换及中值滤波的隧道图像去噪方法研究

A New Denoising Method for Tunnel Image——Research on Tunnel Image Denoising Method Based on Wavelet Transform and Median Filter

利用三维激光扫描仪得到的图像存在噪点,影响后续隧道空间几何测量以及隧道表观病害的检测分析。利用小波变换和中值滤波相结合的方法对得到的隧道图像进行去噪,通过小波变换进行小波分解,得到高频部分,选择合适的阈值,将高频噪声剔除;然后使用中值滤波去除各个子图像的椒盐噪声;最后将图像重构,得到最终去噪后的图像,并引入峰值信噪比进行评价。结果表明,使用此种方法比单独使用中值滤波或小波变换的去噪效果要好。

The image obtained by the 3D laser scanner has noise,which affects the subsequent spatial geometric measurement of the tunnel and the detection and analysis of the apparent disease of the tunnel.The method of combining wavelet transform and median filter is used to denoise the obtained tunnel image.Wavelet decomposition is carried out through wavelet transform to obtain the high frequency part,select the appropriate threshold,and remove the high frequency noise;then use the median filter to remove the salt-andpepper noise of each sub-image.Finally,the image is reconstructed to obtain the final denoised image,and the peak signal-noise ratio is introduced for evaluation.The results show that using this method is better than the median filter or wavelet transform alone.