基于区别缺损对象的视频序列修复方法  

Restoration Method for Video Sequences Based on Distinguishing Damaged Objects

作　　者：刘春英[1] 房庆云[1] 胡维华[1] 

机构地区：[1]杭州电子科技大学计算机学院,杭州310018

出　　处：《计算机科学》2012年第7期267-269,301,共4页Computer Science

基　　金：国家自然科学基金(61004117);浙江省自然科学基金(Y109718)资助

摘　　要：提出了一种基于区别缺损对象的视频序列修复算法。针对第一种缺损采用基于整体变分的空间修复方法;针对第二种缺损采用基于纹理合成的时空修复方法。前者对修复划痕和小斑块时采用的邻域信息进行了重新定位;后者根据视频序列的时间相关性,将匹配块的搜索限定在前后帧中以待修复块中心点为中心的21*21的范围内。实验结果表明,该算法适用于旧的影视资料的修复,可提高修复的效果和效率。A restoration method for video sequences based on distinguishing damaged objects was propose＆ The resto- ration of the first damage is based on total variation algorithm, while the second damage is based on texture synthesis from samples with spatial-temporal correlation. For the former, the eight neighborhoods of target point in scratches and small speckle are repositioned. For the later, the search of match blocks is limited in the 21 ＊ 21 range with repairing block-centered in front and back frames. The experimental results show that the method can improve effectively efficiency and effectiveness for video sequences＇ restoration. It is applicable for roboticized restoration of old film material.

关 键 词：视频修复 划痕 整体变分 邻域 纹理合成 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]