一种桥梁橡胶支座剪切变形自动化检测方法及系统
By introducing a multi-stage corner point extraction strategy based on geometric rule pads for image correction and deep learning image segmentation, combined with linear fitting of the left and right edge contours for tilt angle calculation, the problems of low efficiency and low accuracy in traditional bridge bearing shear deformation detection are solved, and high-precision automated detection of bridge rubber bearings is realized.
CN121883429BActive Publication Date: 2026-07-17UNIV OF SCI & TECH BEIJING
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH BEIJING
- Filing Date
- 2025-12-31
- Publication Date
- 2026-07-17
Smart Images
Figure CN121883429B_ABST
Abstract
本发明提供了一种桥梁橡胶支座剪切变形自动化检测方法及系统，属于工程结构检测技术领域。该发明首先通过引入基于几何规则垫块的图像校正、深度学习图像分割以及“角点粗检测—随机抽样一致性算法精细化定位—轮廓吸附校正”的多阶段角点提取策略，实现了在拍摄空间受限、光照复杂、存在污渍或遮挡等工程现场条件下，仍能对桥梁橡胶支座角点进行高鲁棒性、高精度的自动定位；其次，结合基于左右边缘轮廓线性拟合倾角的剪切变形计算方法，避免了传统人工测量带来的主观误差和重复性差的问题，显著提高了剪切变形检测的精度与稳定性，可在无人值守条件下与监测设备联动，实现桥梁橡胶支座剪切变形的自动化、长期化与智能化监测。
Need to check novelty before this filing date? Find Prior Art