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

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.