景像匹配辅助导航系统中的图像匹配算法研究

图像匹配算法是景像匹配辅助导航系统的核心，而且其性能决定了系统的总体性能，为了提高景像匹配辅助导航系统导航的实时性和精度，就必须选用合适的图像匹配算法，为此，给出了一种快速有效的基于图像特征的图像匹配算法，该算法选用部分Hausdorff距离作为图像匹配时的相似性度量，并利用图像特征提取后的二值化图像进行图像匹配，同时在联合了3种图像匹配加速技术的基础上，将邻域技术引入到图像匹配搜索终止条件中，从而大大提高了图像匹配效率。仿真结果表明，该算法可以保证图像匹配的鲁棒性和有效性，同时，能有效克服图像噪声和几何畸变的影响。该算法实施景像匹配能够在5s以内完成，并与GPS输出周期(1s)相当，可以满足景像匹配辅助导航系统匹配导航的准确性和实时性的性能要求。

The Study of Image Matching Algorithm for Scene Matching Aided Navigation System

The images matching algorithm is the core of the scene matching aided navigation system, whose performance decides the total performance of the system. In order to improve the navigation accuracy and real-time performance of the scene matching aided navigation system, the choice of images matching algorithm must be suitable. The paper has given a quick and effective images matching algorithm based on image features, which has chosen the part Hausdorff distance as the similarity measuring, and utilized the binary images acquired by the image features abstraction to match images, and simultaneous introduced the neighborhood technology to the searching termination condition of images matching based on the combination of three kinds of images matching speed technology, which has improved the effective of the images matching greatly. The results of simulation show that the algorithm can prove the robustness and validity of the images matching and overcome the effect of noises and geometric distortions. The scene matching based on the algorithm can finish within five seconds, which is equivalent to the global position system output frequency (one second). So it can meet the accuracy and real-time performance needs for matching navigation in the scene matching aided navigation system.