Inertia-assisted runway center line stability identification method and device and storage medium
By constructing a list of visual side-pivot position predictions and combining it with inertial navigation data, valid centerlines are selected and strategies are updated. This solves the problem of insufficient robustness of visual centerline recognition during the autonomous take-off and landing of fixed-wing aircraft, and achieves high-precision and stable visual side-pivot position output.
Patent Information
- Application Number
- CN202511398019.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-28
- Publication Date
- 2026-01-13
AI Technical Summary
In existing technologies, visual methods for centerline identification are not robust enough during the autonomous take-off and landing of fixed-wing aircraft. They are prone to false positives and false negatives, especially under complex lighting conditions. Furthermore, they do not fully utilize the high precision and continuity of inertial navigation systems, resulting in weak spatial continuity of centerline detection results.
A list of predicted visual lateral position is constructed, outliers are eliminated and averaged using inertial navigation data, and effective midlines are selected using a modified visual midline recognition algorithm. A sliding window update strategy is adopted to maintain the timeliness of the prediction results.
It achieves continuous and stable high-precision visual side-off position output during aircraft takeoff and landing, improving the robustness and accuracy of visual inspection results and reducing the false detection rate.
Smart Images

Figure CN121330635A_ABST