基于暗原色先验的遥感图像去雾方法

Remote Sensing Image Defogging Based on Dark Channel Prior

针对雾天条件下获得的遥感图像清晰度、对比度和色彩保真度下降,继而影响遥感图像后续应用的问题,考虑到遥感图像数据量大、景深变化小、几乎不含有天空区域的特点,提出一种改进的基于暗原色先验规律的遥感图像快速去雾方法。在保证去雾效果的前提下,对原暗原色先验去雾算法做出了针对性的改进,采用直接求取每个像素点r、g、b三个颜色通道强度值的最小值来获取图像的暗原色图,该方法大幅降低了算法的复杂度,避免了繁重的计算。实验结果表明,改进的去雾算法能够快速有效地去除雾对遥感图像的干扰,提高图像清晰度,还原景物真实色彩,处理时间仅为原算法的2%,可以满足遥感图像实时处理的要求。

Aiming at solving the problems of remote sensing images with poor clarity,contrast and color fidelity in foggy weathers,a rapid defogging method using dark channel prior is proposed based on the characteristics of large amount of data,small changes in depth and almost no area of the sky.To ensure the performance of defogging,the dark channel image is obtained by calculating the minimum value of r,g,b channels.It significantly reduces the complexity and avoids heavy computation.Experimental results demonstrate that the improved algorithm can remove the haze effectively.It can enhance the definition and color of hazy degraded image,and the processing time is 2% of the original method.The proposed algorithm can satisfy the requirement of real-time remote sensing image processing.