无人机视角下的红外图像去模糊算法  

Infrared Image Deblurring Algorithm from Drone s Perspective

作　　者：曹旦夫 齐峰 谭冰 张津溪 闵超[2,3] CAO Dan-fu;QI Feng;TAN Bing;ZHANG Jin-xi;MIN Chao(PipeChina Network Corporation Eastern Oil Storage and Transportation Co.,Ltd.,Xuzhou 221008,China;School of Science,Southwest Petroleum University,Chengdu 610000,China;Artificial Intelligence Research Institute,Southwest Petroleum University,Chengdu 610500,China)

机构地区：[1]国家管网集团东部原油储运有限公司,徐州221008 [2]西南石油大学理学院,成都610000 [3]西南石油大学人工智能研究院,成都610500

出　　处：《科学技术与工程》2024年第20期8767-8775,共9页Science Technology and Engineering

基　　金：国家管网揭榜挂帅项目(WZXGL202106)。

摘　　要：针对油气长输管道采用无人机巡检时所拍摄的红外图像去模糊问题,利用图像通道的先验知识提升模糊图像质量,分别基于双边滤波和非盲去模糊网络NBDN去除人工伪影的方法达到更佳的图像复原效果。首先,基于暗通道先验知识,在最大后验的优化框架中添加暗通道的L_(0)正则项;然后使用图像梯度的L_(0)正则项,代替图像像素的L_(0)正则项作为潜在图像的正则化约束,使用迭代交替估计图像模糊核和中间潜在图像;采用半二次分裂方法和查表法间接优化求解,估计中间潜在图像;采用双线性插值估计图像模糊核,通过对图像进行上下采样,构建图像金字塔,进而利用共轭梯度法直接优化求解。最后,利用估计的模糊核,使用基于超拉普拉斯先验的图像非盲去模糊方法得到潜在图像I_(1);使用基于L_(0)正则化的非盲去模糊方法得到潜在图像I_(0);计算估计的潜在图像I_(1)和I_(0)之间的差值映射,从I_(1)中减去双边滤波过滤后的差分图,得到最终的潜在图像I。将本文算法在低照度图像、含有饱和像素的图像、真实图像以及红外摄像图等图像数据上进行实验,相对于其他图像去模糊算法。实验结果表明:所提出的方法在多种模糊图像复原效果上均具有较强的竞争力。A novel method was proposed to enhance the quality of blurred infrared images captured during unmanned aerial vehicle(UAV)inspections of oil and gas pipelines.The issue of image deblurring was addressed by utilizing prior knowledge of image channels and employing bilateral filtering and the non-blind deconvolution network(NBDN)to remove artificial artifacts.Firstly,the dark channel prior knowledge was incorporated into a maximum a posteriori optimization framework by adding a dark channel L_(0) regularization term.Then,instead of using L_(0) regularization on image pixels,the L_(0) regularization term based on image gradients was employed as the constraint for the latent image.The blur kernel and the intermediate latent image were iteratively estimated through alternating estimation techniques and indirect optimization methods including semi-quadratic splitting and table lookup.The blur kernel was estimated using bilinear interpolation,and an image pyramid was constructed by upsampling and downsampling the image,which were then directly optimized by the conjugate gradient method.Finally,with the estimated blur kernel,a non-blind deblurring method based on the super-Laplacian prior was presented to obtain the latent image I_(1),while another non-blind deblurring method based on L_(0) regularization was also applied to obtain the latent image I_(0).The difference map between I_(1) and I_(0) was calculated and then subtracted from I_(1) by bilateral filtering to obtain the final latent image I.The experiments were designed on low-light images,images with saturated pixels,real images,and infrared camera images to asses the proposed algorithm.The results show that the proposed method has strong competitiveness in various blurry image restoration effects.

关 键 词：数字红外图像 图像去模糊 图像暗通道 双边滤波 非盲去模糊网络 

分 类 号：V279[航空宇航科学与技术—飞行器设计]