一种应用相机阵列实现图像遮挡物移除的方法  

Method of the image de-occlusion by using focal plane camera

作　　者：杨墨轩 赵源萌[1] 朱凤霞 张宏飞 张存林[1] YANG Mo-xuan;ZHAO Yuan-meng;ZHU Feng-xia;ZHANG Hong-fei;ZHANG Cun-lin(Key Laboratory of Terahertz Optoelectronics,Ministry of Education,Beijing Key Laboratory for Terahertz Spectroscopy and Imaging,Beijing Advanced Innovation Center for Imaging Theory and Technology,Department of Physics,Capital Normal University,Beijing 100048,China)

机构地区：[1]太赫兹光电子学教育部重点实验室,太赫兹波谱与成像北京市重点实验室,北京成像理论与技术高精尖创新中心,首都师范大学物理系,北京100048

出　　处：《液晶与显示》2022年第4期494-500,共7页Chinese Journal of Liquid Crystals and Displays

基　　金：国家自然科学基金(No.61875140);首都师范大学分类发展-学位点建设与研究生教育立项及研究生高水平学术创新项目(No.008-2155089);科技创新服务能力建设-基本科研业务(No.20530290044)。

摘　　要：针对光路中前景遮挡物影响感兴趣信息采集的问题,本文对应用相机阵列的遮挡物移除算法进行实验研究。用阵列型光场相机采集四维光场数据,然后用数字重聚焦技术进行不同深度的重聚焦,突出目标物细节特征。利用图像重构技术合成子图像阵列,选择最小误差阈值分割法标记遮挡物区域并复现原图像的细节特征。实验结果证明了应用阵列型光场相机移除遮挡物的可行性,及其改善图像质量、复现遮挡区域图像、提高图像可读性、降低噪声影响的能力。依据无参考的图像质量评价指标,本文算法在重构图像质量上SNR与PSNR分别提升了17.3%与77.6%。In order to address the problem that the foreground occlusions in the light path affect the acquisition of information of interest,this paper explores the de-occlusion algorithm based on the application of the camera array through experiments.The array light field camera is used to collect 4D light field data,after which the digital refocusing technology is employed to perform refocusing at different depths so as to highlight the detailed features of target objects.The experimental results support the feasibility of applying the array light field camera to remove occlusions,as well as its ability to enhance the quality of images,reproduce the image of occluded areas,improve the readability of images,and mitigate the effects of noise.According to the no-reference image quality assessment,in terms of the quality of reconstructed images,the algorithm in this paper can improve the signal to noise ratio(SNR)and peak signal to noise ratio(PSNR)by 17.3%and 77.6%,respectively.

关 键 词：光场采集 数字重聚焦 图像重构 遮挡物 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] O436[自动化与计算机技术—计算机科学与技术]