一种基于多目无人机的桥梁病害图像获取装置及病害检测方法
By combining multi-view drones with multi-functional shooting modules and the independently developed YOLO-FGE model, the problems of low efficiency and insufficient accuracy in traditional bridge defect detection have been solved. This has enabled comprehensive, blind-spot-free, and refined data collection and high-precision defect identification, improving detection efficiency and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Filing Date
- 2025-12-09
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional bridge defect detection methods are inefficient and costly. Furthermore, they are difficult to obtain complete and high-definition images of defects at the bottom of bridges, on curved surfaces of piers, or in environments with insufficient lighting, resulting in insufficient detection accuracy and an inability to identify complex damage in a timely manner.
A bridge defect image acquisition device based on multi-view UAV is adopted, which combines a bottom binocular gimbal camera, a top vertically rotatable multi-functional shooting module and an automatic supplementary lighting system. The YOLO-FGE defect detection model is used for image preprocessing and recognition. The algorithm integrates frequency domain enhancement bottleneck structure, gated multi-scale feature fusion and multi-dimensional collaborative attention mechanism to achieve all-round, blind-spot-free fine data acquisition and defect identification.
It achieves comprehensive and blind-spot-free refined data collection, significantly improving the accuracy and robustness of disease identification, reducing false detection and missed detection rates, improving detection efficiency and safety, and avoiding the risks of personnel working at heights.
Smart Images
Figure CN121725199B_ABST