首页 | 本学科首页   官方微博 | 高级检索  
     

视差信息辅助的视频修补方法
引用本文:高辉,徐玮,张茂军,王云丽,王炜. 视差信息辅助的视频修补方法[J]. 模式识别与人工智能, 2012, 25(3): 462-468
作者姓名:高辉  徐玮  张茂军  王云丽  王炜
作者单位:国防科学技术大学信息系统与管理学院长沙410073
基金项目:国家自然科学基金资助项目
摘    要:提出一种视差信息辅助的街景视频修补方法,首先通过视差图像的分割检测出视频帧中的待修补区域和参考区域,然后同样基于视差信息建立两者的位置对应关系。在具体修补过程中,按照一种摄像机运动相关的修补顺序,采用渐进迭代的策略对整段视频进行修补,最后得到较满意的效果。由于视差信息代表图像之间像素级的位置对应关系,因此该方法的修补效果不受限于场景的复杂度。同时实验证明文中方法能完成较大面积遮挡区域的修补。

关 键 词:纹理修补  视频修补  视差  遮挡移除  
收稿时间:2010-11-01

Disparities Assisted Video Inpainting
GAO Hui , XU Wei , ZHANG Mao-Jun , WANG Yun-Li , WANG Wei. Disparities Assisted Video Inpainting[J]. Pattern Recognition and Artificial Intelligence, 2012, 25(3): 462-468
Authors:GAO Hui    XU Wei    ZHANG Mao-Jun    WANG Yun-Li    WANG Wei
Affiliation:College of Information System and Management,National University of Defense Technology,Changsha 410073
Abstract:A disparities assisted streetscape video inpainting method is proposed. Occlusions in the video are detected and the positional relationship between target region and reference region is built according to the disparities. A camera motion associated filling order as well as a progressive repairing strategy is applied in the proposed method. Because the disparity is a kind of pixel-wise positional relationship between images, the effectiveness of the proposed method is not related with the complexity of the scenes. Furthermore, the experimental results show that the proposed method has the capability to remove occlusions with lager area.
Keywords:Texture Recovery  Video Inpainting  Disparity  Occlusion Removal  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《模式识别与人工智能》浏览原始摘要信息
点击此处可从《模式识别与人工智能》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号