基于DT剖分的二维稠密匹配

2D dense image matching based on delaunay triangulation

提出了一种基于ＤＴ剖分二维稠密匹配方法，即首先对两幅参考图像进行ＤＴ剖分，然后利用对极几何约束完成图像匹配．其特点是避开了费时费力的经典稠密匹配方法，又吸取了ＤＴ剖分的优点，有效地解决了由伸缩引起的匹配点丢失问题。

A new image matching method is proposed based on delaunay triangulation. The first step of this method is making a delauney trianglation of the 2 reference images; the sechond is matching the image points using the epipolar geometry constraint. The method gets rid of the classic timeconsuming dense matching technique and takes advantage of delaunay triangulation. So it effectively resolved the problem of matchmissing caused by lengthening and shortening transformation, and greatly improved the speed and accuracy of mathcing.