基于MRF与引导滤波的声纳图像去噪方法

声纳具有对大范围水下场景探测的能力,一直以来都是水下设备感知外界环境的重要手段,但由于声纳图像分辨率低,海洋环境噪声干扰较为复杂,所以在诸多方面的应用都受到了限制。文中提出了一种基于马尔可夫随机场和引导滤波的声纳图像去噪与增强方法,使用马尔可夫随机场对声纳图像进行预分割,然后采用中值滤波方法对原始图像进行简单滤波处理,最后将该图像作为引导图像对马尔可夫随机场(Markov Random Field,MRF)分割后的图像进行引导滤波实现了对声纳图像的去噪与增强。该方法有效地去除了背景和影子内的噪声,对目标区域内部噪声起到了很好的抑制作用,消除了MRF分割产生的伪轮廓效应,具有较好的边界保持和增强效果。

Study on the De-Noising of Sonar Images Based on MRF and Guided Filtering

Sonars have the capability of detecting wide-range underwater scenes, and have for decades been an important means for subsea equipment to perceive surrounding environment, but their applications are restricted by low resolution and complicated noises in the ocean environment. A novel method based on MRF and guided filtering is designed in this paper for sonar image de-noising and enhancement. Firstly, MRF is used to conduct pre-segmentation, and then, median filtering arithmetic processes primal sonar images in a simple way. This resulting image is regarded as the guided image for filtering the sonar image segmented by MRF, which realizes image de-noising and enhancement. The proposed method could remove noises in background and shadow effectively, restrain the noise within object, eliminate fake contour created by MRF, and has the ability of edge preservation and enhancement.