Full text

Turn on search term navigation

© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

What are the main findings?

Corrugated pipes were identified using semantic segmentation techniques applied to reinforcement cage point clouds acquired by cost-effective RGB-D sensors.

After the segmentation, registration, and fitting processes, an optimal configuration was proposed with maximum measurement errors < 6 mm.

What is the implication of the main finding?

It addresses the limitations of the automatic recognition of corrugated pipes caused by occlusion interference from rebars and precast molds.

It replaces labor-intensive manual work in precast quality control, enhancing the efficiency and precision of the corrugated pipe recognition and measurement.

The accurate installation position of corrugated pipes is critical for ensuring the quality of prestressed concrete box girders. Given that these pipes can span up to 30 m and are deeply embedded within rebars, manual measurement is both labor-intensive and prone to errors. Meanwhile, automated recognition and measurement methods are hindered by high equipment costs and accuracy issues caused by rebar occlusion. To balance cost effectiveness and measurement accuracy, this paper proposes a method that utilizes an RGB-D camera and deep learning. Firstly, an optimal registration scheme is selected to generate complete point cloud data of pipes from segmented data captured by an RGB-D camera. Next, semantic segmentation is applied to extract the characteristic features of the pipes. Finally, the center points from cross-sectional slices are extracted and curve-fitting is performed to recognize and measure the pipes. A test was conducted in a simulated precast factory environment to validate the proposed method. The results show that under the optimal fitting scheme (BP neural network with circle fitting constraint), the average measurement errors for the three pipes are 2.2 mm, 1.4 mm, and 1.6 mm, with Maximum Errors of −5.8 mm, −4.2 mm, and −5.7 mm, respectively, meeting the standard requirements. The proposed method can accurately locate the pipes, offering a new technical pathway for the automated recognition and measurement of pipes in prefabricated construction.

Details

Title
Automated Recognition and Measurement of Corrugated Pipes for Precast Box Girder Based on RGB-D Camera and Deep Learning
Author
Zhu Jiongyi 1 ; Huang Zixin 1 ; Wang, Dejiang 1   VIAFID ORCID Logo  ; Liu Panpan 2 ; Jiang Haili 2   VIAFID ORCID Logo  ; Du, Xiaoqing 1 

 Department of Civil Engineering, School of Mechanics and Engineering Science, Shanghai University, Shanghai 200444, China; [email protected] (J.Z.); [email protected] (Z.H.); [email protected] (D.W.) 
 Shanghai Highway and Bridge (Group) Co., Ltd., Shanghai 200433, China; [email protected] (P.L.); [email protected] (H.J.) 
First page
2641
Publication year
2025
Publication date
2025
Publisher
MDPI AG
e-ISSN
14248220
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3203224369
Copyright
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.