基于可变特征基元的视差估计新方法  

Novel scheme for disparity estimation based on variable feature primitive

作　　者：陈文鑫[1] 陈伟东[1] 朱仲杰[1] 白永强[1] 

机构地区：[1]浙江万里学院宁波市DSP重点实验室,浙江宁波315100

出　　处：《计算机工程与应用》2008年第15期58-60,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.60672073);浙江省自然科学基金(the NaturalScience Foundation of Zhejiang Province of China under Grant No.Y107740);宁波市自然科学基金(the Natural Science Foundation ofNingbo City of China under Grant No.2006A610013);宁波市重点实验室开放基金(No.2007A22002)

摘　　要：视差估计是立体视频和多视点视频信号处理中的一个关键问题。选择可变长线段作为特征基元,提出一种基于特征匹配的视差估计新方法。算法结合唯一性和顺序性约束条件来增强视察估计的可靠性与准确性。在详细介绍了算法的基本原理后进行了实验仿真,实验结果表明新算法能获得较为准确、可靠、亚像素精度的密集视差场,其性能优于固定块匹配(Fixed Size Block Matching,FSBM)、可变块匹配(Variable Size Block Matching,VSBM)等传统的视差估计算法。Disparity estimation is a crucial issue in stereoscopic and multi view video processing.In this paper,a novel scheme for disparity estimation is proposed.The scheme selects variable line segment as feature primitive.The uniqueness constraint and ordering constraint are employed to enhance the accuracy of disparity estimation.The principle of the new scheme is analyzed and experiments are implemented.Experimental results reveal that the proposed algorithm can acquire reliable,sub precise and dense disparity fields and it outperforms the traditional FSBM,VSBM algorithms.

关 键 词：视差估计 立体视频 特征基元 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] TP301.6[自动化与计算机技术—计算机科学与技术]