一种局部多尺度retinex算法在雾天图像中的应用

A local multi-scale retinex algorithm for foggy image

由于大气粒子的散射作用,雾天条件下拍摄的图片质量下降,给户外视觉系统造成严重影响,尤其在宽动态范围场景中的图片存在过度曝光的区域和曝光不足的区域。传统的图像增强方法不能产生令人满意的复原图像,也不能提高图像中每个区域的对比度。单尺度retinex算法和由若干个单尺度retinex算法线性加权而成的多尺度retinex算法都具有局部图像增强和动态范围压缩的特点。文章提出了一种局部多尺度的retinex彩色图像复原(local multi-scale-retinex with color restoration,LMSRCR)算法,该算法根据雾浓度将图像分割成不同的局部区域,再对每个局部区域运行多尺度retinex算法。实验表明,该方法能有效去除图像中的雾,实现彩色退化图像的复原。

Pictures taken under conditions of fog will blur and image contrast is poor due to atmospheric scattering, resulting in a serious impact to the outdoor vision systems, particularly in wide dynamic range scenes. Thus, the images generally consist of both overexposed and underexposed areas. Con- ventional image enhancement methods may either fail to produce satisfactory and undistorted images, or cannot improve every region of interest appropriately. Single-scale retinex（SSR） and multi-scale retinex（MSR） which is defined as a weighted sum of several SSRs are developed for local image con- trast enhancement and dynamic range compression. In this paper, local multi-scale-retinex with color restoration（LMSRCR） algorithm based on multi-scale retinex algorithm is proposed for image defogging. In this algorithm, firstly, the image is divided into different partial regions according to the concentration of the fog. Then, the multi-scale retinex algorithm is run for each partial region. The ex- perimental results show that this method can effectively remove the fog and achieve color restoration of degraded images.