高速微扫描图像超分辨重建  

Super-resolution reconstruction of micro-scanning images

作　　者：赵浩光 曲涵石 王鑫[4] 尚洋[1,5] 刘立刚 韩松伟[4] 孟森[6] 王平 ZHAO Hao-guang;QU Han-shi;WANG Xin;SHANG Yang;LIU Li-gang;HAN Song-wei;MENG Sen;WANG Ping(College of Aerospace Science and Engineering,National University of Defense Technology,Changsha 410073,China;Shenyang Aircraft Design and Research Institute,Aviation Industry Corporation of China,Ltd,Shenyang 110035,China;School of Computer Science and Technology,Xidian University,Xian 710011,China;Department of Airborne Optical Imaging and Measurement,Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;Hunan Provincial Key Laboratory of Image Measurement and Visual Navigation,Changsha 410073,China;IAE Industrial Group Co.,Ltd.,Shanghai 201114,China)

机构地区：[1]国防科技大学空天科学学院,湖南长沙410073 [2]中国航空工业集团公司沈阳飞机设计研究所,辽宁沈阳110035 [3]西安电子科技大学计算机科学与技术学院,西安710071 [4]中国科学院长春光学精密机械与物理研究所航空光学成像与测量重点实验室,吉林长春130033 [5]图像测量与视觉导航湖南省重点实验室,湖南长沙410073 [6]上海乂义实业有限公司,上海201114

出　　处：《光学精密工程》2021年第10期2456-2464,共9页Optics and Precision Engineering

基　　金：森林火情预警监测系统。

摘　　要：为了提升无人机机载光电侦察设备的目标识别距离,本文结合实际工程项目研制了适用于机载光电侦察设备的高速微扫描超分辨核心组件,在嵌入式平台GPU-TX2i上实现了图像实时超分辨重建。首先让微扫描核心组件按照预先设定的步长和频率进行微位移,获取四帧具有亚像素偏差的连续的低分辨率图像,然后使用基于概率分布的图像超分辨重建算法,将这四帧图像处理成一帧高分辨率的图像。实验结果表明,探测器输出的帧频为120 FPS、分辨率为640×512的低分辨图像序列经超分辨重建后,变成帧频为30 FPS、分辨率为1280×1024的图像序列,有效空间分辨率提升了78.2%,目标识别距离提升了43.3%。重建一帧高分辨率图像耗时约为33 ms,微扫描核心组件的微扫描响应时间小于1.0 ms,到位精度小于0.3μm(对应约0.03个像素)满足机载光电侦察设备对实时性和精度的要求。To improve the target recognition distance of the airborne electro-optical reconnaissance equipment of a UAV,this study has developed a high-speed micro-scanning super-resolution core component based on an actual engineering project.The real-time super-resolution reconstruction algorithm is implemented in the embedded platform GPU-TX2i.First,the micro-scanning super-resolution core component moves according to the preset step size and frequency to obtain a continuous image sequence with sub-pixel deviation.Then,the image super-resolution reconstruction algorithm is used based on probability distribution to process the acquired four continuous images into higher resolution images.The experimental results show that the image sequence output achieved by the detector with a frame rate of 120 fps and a resolution of 640×512 is reconstructed via super-resolution and becomes an image sequence with a frame rate of 30 fps and a resolution of 1280×1024.After super-resolution reconstruction,the effective spatial resolution of the image is increased by 78.2%and target recognition distance is increased by 43.3%.The reconstruction time of a high-resolution image is approximately 33 ms.Furthermore,the micro-scanning superresolution core component's micro-scan response time is<1.0 ms and the accuracy in place is<0.3μm(corresponding to approximately 0.03 pixels).These results meet the real-time and precision requirements of airborne electro-optical reconnaissance equipment.

关 键 词：微扫描 超分辨率 图像处理 目标识别 

分 类 号：TP752.2[自动化与计算机技术—检测技术与自动化装置]