计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (33): 195-197.

• 图形、图像、模式识别 • 上一篇    下一篇

一种结合快速灰度投影与SSDA的图像匹配方法

王振江1,2,吴 健1,林方全1   

  1. 1.西北工业大学 计算机学院,西安 710072
    2.空军工程大学 导弹学院,陕西 咸阳 713800
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-21 发布日期:2011-11-21

Image matching method based on fast gray value projection and SSDA

WANG Zhenjiang1,2,WU Jian1,LIN Fangquan1   

  1. 1.School of Computer Science and Technology,Northwestern Polytechnical University,Xi’an 710072,China
    2.Missile Institute,Air Force Engineering University,Xianyang,Shaanxi 713800,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-21 Published:2011-11-21

摘要: 图像匹配作为一种重要的图像处理技术是图像信息融合、目标定位、变化检测等后续工作的重要基础。针对图像匹配应用的实时性要求,该方法按照由粗到细的过程完成匹配,对图像进行多尺度分解,针对高层分解结果图像,采用改进的基于灰度投影的匹配算法进行粗匹配,确定若干符合要求的粗匹配点,并将这些点映射到低层图像的相应区域,在最高层采用序贯相似性检测SSDA进行精细匹配。采用不同遥感图像的实验结果表明了方法的有效性。

关键词: 图像匹配, 小波多尺度塔式分解, 序贯相似性检测

Abstract: As an important image processing technology,image matching is the important foundation for subsequent work,such as the image information integration,targeting,change detection.In order to tackle the problem of the real-time performance,according to a from rough to fine process,the first step is making multi-scale decomposition.It adopts improved gray-scale projection image matching algorithms on the rough result of decomposition for high-level image,then identifies several rough match points which meet the requirements of the threshold value,and gets the corresponding region by mapping these points to the low-level image.Meanwhile,the SSDA is used in fine image matching.The experimental results which derive from remote sensing images certify the validity of the method.

Key words: image matching, wavelet decomposition of multi-scale tower, sequential similar detection