基于结构张量的视频超分辨率算法  

Video super resolution method based on structure tensor

作　　者：严宏海 卜方玲[1] 徐新[1] 

机构地区：[1]武汉大学电子信息学院,武汉430079

出　　处：《计算机应用》2016年第7期1944-1948,1987,共6页journal of Computer Applications

基　　金：国家863计划项目(2013AA122301)~~

摘　　要：针对传统正则化超分辨率（SR）重建模型中,正则化参数选择过大会使重建结果模糊,导致边缘和纹理等细节丢失,选择过小模型去噪能力又不足的问题,提出一种基于结构张量的双正则化参数的视频超分辨率重建算法。首先,利用局部结构张量对图像进行平滑区域和边缘的检测;然后,利用差异曲率对全变分（TV）进行先验信息加权;最后,对平滑区域和边缘采用不同的正则化参数进行超分辨率重建。实验数据显示提出的算法将峰值信噪比（PSNR）提高了0.033~0.11 d B,具有较好的重建效果。实验结果表明：该算法能够有效地提升低分辨率（LR）视频帧重建效果,可应用于低分辨率视频增强、车牌识别和视频监控中感兴趣目标增强等方面。The parameter of traditional regularized Super Resolution（ SR） reconstruction model is difficult to choose： the higher parameter value results in blurred reconstruction and the fading of edge and detail, while the lower parameter value weakens the denosing ability. A double regularization parameters super resolution reconstruction method based on structure tensor was proposed. Firstly, smooth region and edge was detected by using local structure tensor. Secondly, the Total Variation（ TV） was weighted with the priori information of difference curvature. Finally, two different parameters toward smooth region and edge were used to reconstruct super resolution image. The experimental data show that the proposed algorithm can improve the Peak Signal-to-Noise Ratio（ PSNR） of 0. 033- 0. 11 d B, and get better reconstruction results. The proposed algorithm can effectively improve the reconstruction effect of Low Resolution（ LR） video frames, and can be applied to LR video enhancement, license plate recognition and the interest target enhancement in video surveillance, etc.

关 键 词：超分辨率 帧序列 结构张量 双正则化参数 全变分加权 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP391.413[自动化与计算机技术—计算机科学与技术]