基于闪动快门的互补序列对的运动模糊图像复原  

Motion Blurred Image Restoration Based on Complementary Sequence Pair Using Fluttering Shutter Imaging

作　　者：叶晓杰 崔光茫 赵巨峰[1,2] 朱礼尧 YE Xiao-jie;CUI Guang-mang;ZHAO Ju-feng;ZHU Li-yao(School of Electronics and Information,Hangzhou Dianzi University,Hangzhou 310018,China;Zhejiang Provincial Key Lab of Equipment Electronics,Hangzhou 310018,China)

机构地区：[1]杭州电子科技大学电子信息学院,杭州310018 [2]浙江省装备电子研究重点实验室,杭州310018

出　　处：《光子学报》2020年第8期155-169,共15页Acta Photonica Sinica

基　　金：国家自然科学基金(No.61805063);浙江省自然科学基金(Nos.LGF20F050003,LY18F050007)。

摘　　要：针对传统曝光模式下运动模糊图像复原的病态性问题,提出了一种基于闪动快门互补序列对的运动模糊图像复原方法.分析了闪动快门成像原理及其码字序列在频域的相关特性,结合编码序列对之间的信息互补特点,引入Golay互补序列生成理论,构建长度适中的二进制闪动快门互补序列对.互补序列对的联合调制传递函数在频域上实现了信息互补,其曲线对比单码字的调制函数具有更大的最小值和更小的方差值,且其构成了峰值-谷值对应,保证了互补图像序列能够相互补偿由于运动模糊所造成的空间信息损失.引入全变分正则化模型,构造一体化的多帧图像去模糊复原算法框架,实现清晰图像的有效获取.搭建了运动目标实拍仿真成像平台,开展了仿真和实拍运动模糊复原实验.实验结果表明,该方法能够更好地保留场景细节信息,获得高质量的运动模糊复原结果,有效改善复原过程中的负效应.相较于其他几种运动目标成像获取方式,该方法复原图像具有更好的主客观评价结果.Aiming at the ill posed problem of motion blurred image restoration in traditional exposure mode,a method of motion blurred image restoration based on complementary sequence pairs of fluttering shutter is proposed.The imaging principle of fluttering shutter and the correlation characteristics of code sequence in frequency domain are analyzed.Combined with the information complementarity characteristics between coding sequence pairs,the Golay complementary sequence generation theory is introduced to construct binary fluttering shutter complementary sequence pairs with moderate length.The joint modulation transfer function of complementary sequence pair realizes information complementarity in frequency domain,its curve has a larger minimum value and a lower variance value than the modulation function of the single code word,and it forms peak valley correspondence,which ensures that complementary image sequence can compensate each other for spatial information loss caused by motion blur.The total variation regularization model is introduced to construct an integrated multi frame image deblurring restoration algorithm framework to achieve effective acquisition of clear images.A real-time simulation imaging platform for moving objects is built,and experiments of simulation and real-time motion blur restoration are carried out.The experimental results show that the proposed method can better retain the details of the scene,obtain high-quality motion blur restoration results,and effectively improve the negative effects in the restoration process.Compared with other acquisition methods of moving target imaging,the proposed method has better subjective and objective evaluation results.

关 键 词：图像处理 图像复原 闪动快门 运动模糊图像 联合调制传递函数 全变分正则化 

分 类 号：TN911.73[电子电信—通信与信息系统]