基于质量评价最优的无人机航拍图像去雾方法

Image Dehazing Based on the Optimum of UAV Aerial Image Quality Evaluation

无人机是现代化战争的重要信息侦察手段,雾气严重影响到无人机拍摄图像的质量,对侦察识别的执行能力起到妨碍作用。为提高雾气环境下无人机航拍图像有效利用性,针对无人机航拍图像的特点及特殊应用背景,提出一种质量评价最优的无人机航拍图像去雾方法。通过将信息熵、标准差和图像傅里叶振幅3种图像质量评价参数相结合,建立图像质量综合评价函数;给定不同的大气透射率值,求解相应的去雾图像,以去雾图像的质量评价函数值作为择优标准。研究结果表明:该方法计算复杂度低、操作简单、简便易行,易于操作与实现;所获得的去雾图像视觉效果清晰、结果误差小。

UAV is an important means of information reconnaissance in modern warfare.The fog seriously affects the quality of UAV aerial images and hinders the ability to perform reconnaissance and recognition.In order to improve the effective utilization of UAV aerial images in the foggy environment,an image dehazing method based on the optimum of UAV aerial image quality evaluation is proposed according to the characteristics and special application background of UAV aerial images.A comprehensive image quality evaluation function is established by combining three image quality evaluation parameters,such as information entropy,standard deviation and image Fourier amplitude.Different atmospheric transmittance values are given,the corresponding dehazing image is solved,and the quality evaluation function value of dehazing image is used as the screening standard.The experimental verification shows that the image dehazing method based on the optimum of UAV aerial image quality evaluation has low computational complexity and simple operation.And the obtained dehazing image has clear visual effects and small result errors.