Research on real-time matching algorithm based on robust Hausdorff distance

In allusion to requirement of real time and high accuracy in airborne image aided navigation system an algorithm based on robust Hausdorff distance of airborne remote image real time matching is put forward. Because of great information in remote image at first wavelet transform is used to acquire low frequency component to realize image compression to decrease calculation work and increase matching speed, and modified invariant moment is done to correct image distortion, then robust Hausdorff distance is used to realize remote image real time matching to acquire high matching precision, simulative experiment is done. Simulative experiment proves that the matching of a remote sensing image and a template image can be fulfilled about 1.6 second, the algorithm is robust and effective, and real time image navigation can be achieved.