惯性组合导航系统中的快速景象匹配算法研究

在景象匹配辅助导航中，特征点的选取是提高图像匹配速度、精度和鲁棒性的关键之 一。景象匹配中要求提取出的特征是那些可靠性高、辨别性强、计算量小的不变特征。提出 了基于SIFT特征的导航用快速景象匹配算法。算法首先针对惯性组合导航的工作特点， 对SIFT特征点检测及特征点匹配进行了优化设计，然后用RANSAC方法过滤掉错误匹配点，最 后，进行最小二乘精确匹配算法获取航向和位置偏差信息。实验分析了算法对不同分辨率图 像和不同区域的匹配适应性，抗噪声性能，匹配精度以及实时性，并与基于部分Hausdorff 距离的边缘特征景象匹配算法进行了对比。实验结果表明，算法的性能优越，在匹配速度、 精度和鲁棒性方面都优于部分Hausdorff距离算法，可以满足景象匹配导航系统匹配修正的 高性能要求。

Research on the Fast Scene Matching Algorithm in the Inertial Integrated Navigation System

In the scene matching aided navigation system, selection of image features is the one, of the key ways of improving the speed, accuracy and robustness of image matching. The features must be highly reliable, distinctive, and computed efficiently. In this paper, we propose the scene matching algorithm based on SIFT features for navigation. Firstly, we optimize the Process of detection of the SIFT features "and feature matching especially for the inertial integrated navigation. Then, we. adopted RANSAC algorithm to remove the false matching points, finally, the least square algorithm is applied for getting both the aircraft position errors and course deviation.In the experiment, we analyze adaptability of the algorithm for the different resolution imges and different regions of an image, perfor-mance of noise resistance, matching accuracy and real-time performance. The experiment result demonstrates the superiority of algorithm in matching speed, accuracy and robustness in contrast with scene matching algorithm based on hausdorff distance, so it can meet the high performance needs for matching navigation in the scene matching aideed navigation system.