双相机系统的高分辨率重建  

High Resolution Reconstruction for Dual-Camera System

作　　者：陈锦伟[1] 赵巨峰[2] 

机构地区：[1]浙江省计量科学研究院,浙江杭州310018 [2]杭州电子科技大学,浙江杭州310018

出　　处：《北京理工大学学报》2016年第2期175-180,共6页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(61405052)

摘　　要：为获取高分辨大视场的目标图像,提出了双相机系统的高分辨重建算法.根据小视场高/低分辨图像对,学习图像的高频特征,利用线性回归函数表征图像高分辨与低分辨的高频特征映射关系;在小波域实现低分辨、大视场目标图像的超分辨重建,使其达到高分辨、小视场目标图像的分辨率水平;设计了10组双相机系统的仿真实验,并与双三次插值、小波域插值和学习自身的重建等3种流行算法进行对比.实验结果表明,本文算法取得了最好的重建效果,时间代价也相对较小,并且重建评价指标PSNR比传统双三次插值高约0.26.To obtain the wide FOV target image with high resolution,a high resolution reconstruction for dual-camera system was proposed.Firstly,the high frequency feature was learnt based on high/low resolution image pair with narrow FOV,and a linear regression function was trained to represent the mapping of high frequency feature between high resolution and low resolution.Then,the super resolution reconstruction of wide FOV image was realized in wavelet domain.At last,ten groups of simulation experiments were carried out to verify proposed high resolution for dual-camera system,comparing with popular bicubic interpolation,wavelet based interpolation and self-similarities based reconstruction.Experimental results showed that the proposed approach performs best with small time cost,whose PSNR was higher than bibubic interpolation about 0.26.

关 键 词：双相机系统 超分辨重建 小波变换 线性回归函数 图像插值 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]