An ascending and descending rail radar image matching method and device, electronic equipment and medium
By using geocoding and geometrically guided normalization of view-sensitive consistency maps, combined with a multi-constraint matching strategy, the problem of adaptability to geometric changes between ascending and descending SAR images was solved, achieving high-precision image matching and positioning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA SURVEY SURVEYING & MAPPING TECH
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing SAR image matching methods are not adaptable enough to geometric changes between ascending and descending orbit images, resulting in a small number of matching points or a high mismatch rate, making it impossible to achieve high-precision geometric processing and information extraction.
A unified spatial benchmark is established through geocoding, a view-sensitive consistency map is constructed and geometrically guided normalization is performed, a reliable matching point set is selected by combining a multi-constraint matching strategy, and image registration is performed using a second-order polynomial geometric mapping model.
It improves the robustness and positioning accuracy of SAR image matching under conditions of large viewing angle differences, and provides high-quality geometric reference data to support joint positioning and deformation monitoring of SAR images from different orbits.
Smart Images
Figure CN122415696A_ABST