沉浸式视频中三维场景的视差精炼方法  

Refine disparity estimate method of 3D scene in immersive video

作　　者：吕小倩[1] 陈辉[1] 王玉锐[1] 唐丽焕[1] 

机构地区：[1]山东大学信息科学与工程学院,济南250100

出　　处：《计算机工程与应用》2009年第19期157-159,共3页Computer Engineering and Applications

基　　金：山东省自然科学基金(No.Z2005G02);山东省中青年科学家科研奖励基金(No.03BS001)~~

摘　　要：视差估计是多视点视频中的关键技术,针对沉浸式视频中丰富的场景信息,给出一种有效的提取精炼视差图的方法。对左右图像进行平滑及基于颜色的分割,然后利用像素增益直方图得到的匹配函数计算初始视差空间分布(DSD),通过执行平滑限制和连续性限制来精炼DSD,最后进行一定的平滑处理。实验结果表明该方法能得到精确光滑的视差图,有利于获得高质量的中间视。Disparity estimate is a key technique of multi-view video.Facing a plentiful of environment information in immersive video,this paper presents a efficient method to estimate and refine the disparity.Firstly,the left and right images are smoothed and then segmented based on colors.Secondly,the initial DSD is computed using the matching function,which is found by histogram of pixel gains.Next,a smoothness constraint and a consistency constraint are enforced to refine the DSD.Lastly,some smoothing measures are taken.Experimental results show that more precise and smooth disparity field can be acquired with the proposed method,and it is good for obtaining the intermediate views with high quality.

关 键 词：沉浸式视频 多视点视频 视差精炼 基于颜色分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]