Method and system for detecting road cracks based on unmanned aerial vehicle image
By fusing visible light and thermal infrared images and utilizing histogram analysis and Gaussian thermal diffusion rules, the problem of background noise interference in road crack detection was solved, achieving high-precision crack identification and damage assessment, and improving the accuracy and reliability of the detection results.
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUIZHOU JIAOJIAN INFORMATION TECH CO LTD
- Filing Date
- 2026-04-09
- Publication Date
- 2026-05-29
AI Technical Summary
Existing methods for detecting road surface cracks based on UAV imagery are susceptible to interference from complex background noise, leading to segmentation errors and failing to effectively quantify and assess the damage status of the internal structure of the cracks.
A dual-modal sensor is used to acquire visible light and thermal infrared images. Histogram analysis is used to locate abnormal regions in the thermal infrared images, seed points are extracted and mapped to the visible light images, and Gaussian thermal diffusion rules and image structure similarity analysis are combined to accurately detect and correct crack regions. The temperature distribution of the crack skeleton is quantified to assess the damage state.
It effectively suppresses interference from complex background noise, improves the accuracy of pavement crack detection, and realizes quantitative assessment from two-dimensional appearance morphology to internal damage state, providing a reliable basis for road maintenance decisions.
Smart Images

Figure CN121982596B_ABST
Abstract
Citation Information
Patent Citations
Airport pavement crack detection method based on infrared and visible light image data fusion
CN110246130A
Crack detection method and system for expressway construction
CN120404748A