A method for identifying and quantifying micro-fissure width of concrete based on improved skeleton method
By using an improved skeleton method, combined with monocular camera calibration and AprilTag codes, and employing the PnP algorithm and LM optimization, the problem of accuracy in identifying and quantifying the width of micro-cracks in concrete was solved, achieving high-precision crack detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- EAST CHINA JIAOTONG UNIVERSITY
- Filing Date
- 2026-03-26
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately identify and quantify the width of micro-cracks in concrete, resulting in insufficient accuracy and robustness of test results, which in turn affects structural durability and safety.
An improved skeleton method is adopted, which combines monocular camera calibration, AprilTag code, PnP algorithm and LM optimization. Through image processing and visual perception technology, distortion is gradually corrected, skeleton points are extracted, and crack width is dynamically weighted and fused to calculate.
It achieves high-precision identification and quantification of the width of micro-cracks in concrete, improves the accuracy and robustness of the detection results, and ensures high precision of pose parameters and accuracy of crack segmentation.
Smart Images
Figure CN122415451A_ABST