An automated matching method for stereoSAR images based on geometry constraint

作者：Wang Yachao^*; Zhang Jixian; Deng Kazhong; Huang Guoman; Yang Shucheng

来源：Journal of China University of Mining & Technology, 2015, 44(1): 164-169.

• Automated matching
• Geometry constraints
• Matching algorithm
• Normalized cross correlation
• Original images
• SAR Images
• Scale invariant feature transforms
• SIFT

Considering the difficulty to identify matches in stereo SAR images, an automated matching algorithm for stereo SAR images based on geometry constraint was proposed. In this algorithm, scale invariant feature transform (SIFT) matching algorithm was firstly applied on the multi-look images, and false matches were rejected according to the geometric consistency. Then matching propagation based on the geometry constraint with grid control was utilized to get more and well-distributed matches, and the matches can be modified based on normalized cross correlation (NCC). Finally, the matches were converted to coarse matches of original images, and on the basis of more accuracy geometry constraint, the coarse matches can be modified. The same-side airborne SAR images of X band obtained from different angles are implemented in experiments. Compared with classic SIFT matching algorithms, the results demonstrate that the proposed algorithm has significant improvement in terms of the amount, precision and distribution of matches.

• 出版日期2015
• 单位中国矿业大学（北京）