Research of scene matching algorithm based on regions
一种基于区域特征的景象匹配算法研究

Scene matching is core technology of the vehicle matching aided navigation system. Improving the correct matching rate is the difficult point and hotspot in research. This paper proposed a scene matching algorithm based on regions feature. Its basic method was: extracting the regions feature of the reference image and real image and computing the gray value, shape parameter, texture information and variance of region as the decisive factors to design the similarity measurement function firstly; then computing the Hausdorff distance of the region pair to decide whether corresponding regions or not. Plenty simulation experiments show that the matching time may achieve 0. 138 s, the best correct matching rate is 92. 67%. The result shows the algorithm not only meets the requirements of the scene matching, but also improves the matching time and correct rate greatly, and has practical value for the positioning of the navigation system.