计算机应用 ›› 2011, Vol. 31 ›› Issue (01): 163-166.

• 图形图像处理 • 上一篇    下一篇

彩色图像对自适应匹配算法

刘效勇1,李大海1,王琼华2,刘曦1,漆小平1   

  1. 1. 四川大学
    2. 四川大学电子信息学院
  • 收稿日期:2010-06-18 修回日期:2010-07-20 发布日期:2011-01-12 出版日期:2011-01-01
  • 通讯作者: 李大海
  • 基金资助:
    国家自然科学基金

Adaptive stereo matching algorithms for color stereo images

  • Received:2010-06-18 Revised:2010-07-20 Online:2011-01-12 Published:2011-01-01
  • Supported by:
    The Natural Science Foundation of China

摘要: 提出了两种方法来提高图像匹配的精度。一种方法是改变自适应匹配窗口的选择方法,与原来的矩形窗口相比较,提出的窗口选取方法能在低纹理区域得到包含有效信息量更多、更接近实际边界的窗口。此外,通过降低边界点相似度在计算过程中的权重来降低边界点影响力,使得视差不连续区域的匹配精度得到提高。算法采用了Middlebury网站上提供的四幅立体图像对Tsukuba、Venus、Teddy和Cones分别进行实验验证。实验表明文中提出的两种方法对四幅图像的匹配精度均有所提高。

关键词: 立体匹配, 自适应匹配窗, 彩色相似度, 边界点匹配, 视差图

Abstract: Two algorithms are proposed in this article to improve the matching of stereo image pairs. One is the improved algorithm of adaptive image window. Compared with the previous rectangle image window, the new image window obtained by the improved algorithm includes more intensity variations in low texture areas. It becomes more effective to make the new image window approach the real edge of a certain texture area in the stereo image pairs. The other is the improved algorithm in edge pixel areas, which is used to enhance the correction rate of matching the edge pixels by decreasing the Corr (color correlation measurement) of the edge pixels. These two algorithms are investigated by matching four stereo images (Tsukuba, Venus, Teddy and Cones) with ground truth provided in Middlebury stereo database.

Key words: stereo matching, adaptive image window, color correlation measurement, edge pixel matching, parallax image