Application of Weighted Hausdorff Distance Algorithm in SAR/INS Scene Matching
Xing Guang-hua · Kongzhi yu juece · 2006
A weighted Hausdorff distance image matching algorithm based on extracting bifurcating points on feature image is proposed.The corresponding weight formula is also put forward.A preprocessing of thinning the binary image is presented to meet the real-time need of scene matching aided navigation system.This preprocessing can reduce the redundancy of the database and speed up the global search time.Then,based on the bifurcating points extracted from thinning image,the application of the weighted Hausdorff distance algorithm to image matching can overcome the effect of speckle noise in the synthetic aperture radar(SAR) image.Simulation shows that this algorithm meet the real-time and accuracy needs of SAR/INS scene matching aided navigation system.