基于MAP框架的时空联合自适应视频序列超分辨率重建  

Spatio-temporal Adaptive Super-resolution Reconstruction of Video Sequence Based on MAP Frame

作　　者：张冬明[1,2] 潘炜[1] 陈怀新[2] 

机构地区：[1]西南交通大学信息科学与技术学院光通信与光器件研究所,成都610031 [2]中国电子科技集团公司第十研究所,成都610036

出　　处：《自动化学报》2009年第5期484-490,共7页Acta Automatica Sinica

基　　金：国家自然科学基金(10174057,90201011);高等学校博士学科点专项科研基金(20070613058)资助~~

摘　　要：超分辨率重建在视频监控、高清晰度电视、遥感图像、医学图像处理等领域具有广阔的应用前景.最大后验估计(maximum a posteriori,MAP)法是普遍采用的一种超分辨率重建方法.针对传统MAP法存在的局限性,本文提出了一种基于MAP框架的时空联合自适应视频序列超分辨率重建算法.时空联合自适应机制的引入使得算法在保持边缘的同时可减小错误运动估计矢量对重建图像质量的影响.实验结果表明,算法具有重建质量好、边缘保持能力强、收敛速度快等特点.Super-resolution reconstruction is an important research topic for video surveillance, HDTV, remote sensing, medical imaging, etc. The MAP （Maximum a posteriori） algorithms are widely used for super-resolution reconstruction. In this paper, a novel spatio-temporal adaptive super-resolution reconstruction algorithm of video sequence based on MAP frame is proposed to overcome the weakness of conventional MAP algorithms. The spatio-temporal adaptive mechanism, which is induced to MAP super-resolution reconstruction frame, can not only preserve edges but also prevent reconstructed image from the influence of inaccurate motion vectors to some extent. Experimental results demonstrate that the proposed algorithm can preserve edges of the reconstructed image effectively with good reconstructed quality and fast convergence speed.

关 键 词：超分辨率 最大后验估计 边缘保持 图像先验模型 时空联合自适应 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]