首页 | 本学科首页   官方微博 | 高级检索  
     

基于图割的高质量深度图获取方法
引用本文:左一帆,安平,张兆杨. 基于图割的高质量深度图获取方法[J]. 电视技术, 2011, 35(15): 37-40
作者姓名:左一帆  安平  张兆杨
作者单位:上海大学通信与信息工程学院,上海200072;新型显示技术及应用集成教育部重点实验室,上海200072
基金项目:国家自然科学基金重点项目(60832003); 上海市科委重点项目(10510500500)
摘    要:3DTV作为下一代视频广播系统,还有许多技术难点有待解决,其中深度估计是3DTV的关键技术之一。为了获取高质量的深度图,提出基于图割(graph cut)的深度估计方法。该算法在构建能量函数的数据项时,通过对窗口内各个像素赋予自适应权重,引入梯度信息以抑制因亮度差异导致的误匹配问题并保护边缘信息。然后,经过交叉检测将深度图像素分为可靠点与不可靠点两类。对检测后的深度图进行后处理迭代优化,从而提高所获取深度值的可靠性。实验表明此算法估计出的深度图用VSRS绘制虚拟合成视时比标准的深度估计软件DERS5.1可有效提高虚拟视质量。

关 键 词:多视点  深度图估计  图割

High Quality Depth Map Estimation Method Based on Graph Cut
ZUO Yifan,AN Ping,ZHANG Zhaoyang. High Quality Depth Map Estimation Method Based on Graph Cut[J]. Ideo Engineering, 2011, 35(15): 37-40
Authors:ZUO Yifan  AN Ping  ZHANG Zhaoyang
Affiliation:ZUO Yifan1,2,AN Ping1,ZHANG Zhaoyang1,2(1.School of Communication and Information Engineering,Shanghai University,Shanghai 200072,China,2.Key Laboratory of Advanced Display and System Application of the Ministry of Education,China)
Abstract:As the next generation of broadcast system,there are many technical difficulties need to be resolved in 3DTV,in which depth estimation is one of the key techniques.To improve the depth estimation precision,a novel depth estimation method based on graph cut is proposed in this paper.A local window with adaptive support weights is used to compute the average value difference of the pixels' luminance,which is a part of data item of the cost function.To resist mismatch caused by brightness difference and protec...
Keywords:multi-view video  depth map estimation  graph cut  
本文献已被 CNKI 万方数据 等数据库收录!
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