影像数据的获取受到传感器、大气、光照等多种因素影响,影像数据本身即存在成像的不确定性,且用于匹配的影像数据间常存在较大的尺度、旋转差异,因此利用传统的基于区域灰度的匹配方法很难实现遥感影像的自动匹配。针对遥感影像数据的复杂性,结合不变矩的优良性质,提出一种基于地物结构特征的影像自动匹配方法。首先基于RANSAC(random sample consensus)算法提取影像直线特征,并进一步根据地物构造特征,在直线特征的基础上,设计并实现结构特征提取方法;然后利用结构特征的不变矩及空间相似性测度自动检测最优匹配特征对,实现影像的初始匹配;最后采用松弛匹配等方法,并对松弛匹配结果进行优化,实现影像全局匹配。为了验证算法性能,采用仿真数据和实地遥感影像进行测试,实验结果表明,本文方法不受旋转、缩放等因素影响,能实现遥感影像的自动快速匹配。

Because of the uncertainty of imaging, large scales, and rotation difference between the match data, the traditional intensity-based matching methods are not meeting our demands. For the complexity of the remote sensing data, we developed an image matching method based on the features of the structure characteristics, combined with the excellent properties of invariant moments. At first, we are extracting image linear characteristics based on RANSAC (random sample consensus) and further extracting the structure feature. Next, we are getting the optimal matching by the invariant moment and space correlation, realizing the initial image matching. Finally, using relaxation matching method, we realize the global image matching. Experimental results show that this method is not affected by rotation, and zooming factors and it can realize an automatic and quick remote sensing image matching.