一种基于机器视觉的混凝土表面微裂缝识别方法及系统
By acquiring time-series images and temperature data of concrete surfaces, performing image preprocessing and correlation analysis, the accuracy and stability issues of identifying microcracks on concrete surfaces in existing technologies have been resolved, enabling accurate identification and health status assessment of thermally induced cracks.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HOHAI UNIV
- Filing Date
- 2025-12-09
- Publication Date
- 2026-07-17
AI Technical Summary
Existing machine vision-based methods for identifying microcracks on concrete surfaces struggle to achieve continuous and reliable identification of microcracks when faced with periodic temperature changes, especially given the dynamic changes caused by the thermal expansion and contraction of concrete structures, resulting in insufficient accuracy and stability.
By acquiring time-series image data of concrete surfaces and ambient temperature data, image preprocessing is performed to extract candidate crack regions, calculate the information entropy change trend of texture feature sequences, and analyze the correlation between texture features and ambient temperature to identify thermally induced cracks.
It enables quantitative description and judgment of the dynamic changes of microcracks on concrete surfaces, improves the accuracy and reliability of crack identification, can distinguish between real crack changes and noise interference, and provides a basis for assessing the health status of concrete.
Smart Images
Figure CN121682306B_ABST