In the SAR/INS integrated navigation system, SAR images have a serious distortion and serious speckle noises.
Therefore, this paper presents the image matching algorithm of SAR/INS integrated navigation system based on CenSurE.
The process of the image matching algorithm is designed especially for the inertial integrated navigation. Firstly, CenSurE
features and upright SURF descriptor are extracted. And the features are matched by using cosine similarity measure.
Finally, the GroupSAC algorithm and the least square algorithm are used to get the high accurate aircraft position and course
deviation. Performance evaluation experiments for scene matching show that, CenSurE detector is superior in matching
adaptability, speed, accuracy and robustness, which can meet the high performance needs for matching navigation in the
SAR/INS integrated navigation system.