结合精确大气散射图计算的图像快速去雾

提出一种基于精确大气散射图的单幅图像快速去雾算法.首先基于大气散射光的特性,充分利用双边滤波保边缘的平滑特性,估测大气散射光和图像局部对比度,并通过引入像素值与平均灰度值的比较,得出更加准确的大气散射图,然后根据大气散射模型复原雾天图像.通过对获得的结果图像进行色调调整和局部去噪的优化处理,得到一幅视觉上较真实的清晰无雾图像.通过与几种典型的图像去雾算法比较,表明本文算法对于远景和深度发生突变的位置可以获得更好的去雾效果.同时,本文算法的时间复杂度与图像大小成线性关系,并且由于本文算法可以并行运行,因此可以进一步采用GPU加速,从而使得本文算法可以满足实时应用的需求.

Fast image dehazing based on accurate scattering map

In this paper, we propose a new fast dehazing method from a single image based on an accurate scattering map. First, based on the characteristics of atmospheric scattering light, we take full advantage of the edge-preserving feature of bilateral filtering to estimate the atmospheric scattering light and the local contrast of the image. Then, by introducing the comparison of pixel values and the average gray value, we get a more accurate scattering map to restore the scene radiance using the atmosphere attenuation model. Finally, we optimize the recovered image by tone mapping and local denoising to get a more realistic and clear image. Compared with the exiting state-of-the-art dehazing methods, our method could get better dehazing effect at distant scenes and places where depth changes abruptly. Our method is fast with linear complexity in the number of pixels of the input image. Furthermore, our method can be performed in parallel, thus, it can be further accelerated using GPU, which makes our method applicable for real-time requirements.