东南大学学报（英文版）2025，Vol.41Issue(3)：278-285,8.DOI:10.3969/j.issn.1003-7985.2025.03.003
基于深度学习和计算机视觉的桥梁预制箱梁截面几何参数识别
Geometric parameter identification of bridge precast box girder sections based on deep learning and computer vision
摘要
Abstract
To overcome the limitations of low efficiency and reliance on manual processes in the measurement of geomet-ric parameters for bridge prefabricated components,a method based on deep learning and computer vision is devel-oped to identify the geometric parameters.The study uti-lizes a common precast element for highway bridges as the research subject.First,edge feature points of the bridge component section are extracted from images of the precast component cross-sections by combining the Canny operator with mathematical morphology.Subsequently,a deep learn-ing model is developed to identify the geometric parameters of the precast components using the extracted edge coordi-nates from the images as input and the predefined control pa-rameters of the bridge section as output.A dataset is gener-ated by varying the control parameters and noise levels for model training.Finally,field measurements are conducted to validate the accuracy of the developed method.The re-sults indicate that the developed method effectively identi-fies the geometric parameters of bridge precast components,with an error rate maintained within 5%.关键词
桥梁预制构件/截面几何参数/尺寸识别/计算机视觉/深度学习Key words
bridge precast components/section geometry parameters/size identification/computer vision/deep learning分类
交通工程引用本文复制引用
贾景伟,倪有豪,茅建校,徐寅飞,王浩..基于深度学习和计算机视觉的桥梁预制箱梁截面几何参数识别[J].东南大学学报（英文版）,2025,41(3):278-285,8.基金项目
The National Natural Science Foundation of China(No.52338011,52378291),Young Elite Scientists Sponsorship Pro-gram by CAST(No.2022-2024QNRC0101). （No.52338011,52378291）
