A scene matching method with weighted hausdorff distance based on edge measure

According to the classical methods based on Hausdorff distance which only consider the geometric relationship among the edge feature points and don't be taken into account the difference contribution of feature points to image matching, a simple but efficient real-time image matching aided navigation algorithm with weighted Hausdorff distance based on edge measure (EM-WHD) is proposed. Given a reference image and a sensed image, edge measure function is constructed based on the structure tensor method and ratio of average method. Furthermore, edge points are extracted. The weighted Hausdorff distance based on edge measure function and edge measure difference between matched edge points is carried out to match images. Simulation results show that this novel method is effective and can increase the computational speed.