计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (15): 58-60.

• 理论研究 • 上一篇    下一篇

基于可变特征基元的视差估计新方法

陈文鑫1,陈伟东1,朱仲杰1,2,白永强1,2   

  1. 1.浙江万里学院 宁波市DSP重点实验室,浙江 宁波 315100
    2.郑州大学 物理工程学院,郑州 450001
  • 收稿日期:2007-09-25 修回日期:2007-12-14 出版日期:2008-05-21 发布日期:2008-05-21
  • 通讯作者: 陈文鑫

Novel scheme for disparity estimation based on variable feature primitive

CHEN Wen-xin1,CHEN Wei-dong1,ZHU Zhong-jie1,2,BAI Yong-qiang1,2   

  1. 1.Ningbo Key Lab of DSP,Zhejiang Wanli University,Ningbo,Zhejiang 315100,China
    2.Physical Engineering College,Zhengzhou University,Zhengzhou 450001,China
  • Received:2007-09-25 Revised:2007-12-14 Online:2008-05-21 Published:2008-05-21
  • Contact: CHEN Wen-xin

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。

关键词: 视差估计, 立体视频, 特征基元

Abstract: 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.

Key words: disparity estimation, stereo video, feature primitive