Journal Home > Volume 1 , Issue 2
Journal of Intelligent Construction 2023, 1(2): 9180010 https://doi.org/10.26599/JIC.2023.9180010
Research Article | Open Access | Issue | Published: 21 July 2023

Multi-volume variable scale bitmap data object classification algorithm architectural concrete color difference detection

Show Author's Information Gang Yao1,2,  Wentong Sun1,  Yang Yang1,2( ),  Mingpu Wang1,  Rui Li1,  Yuanlin Zheng1,3
School of Civil Engineering, Chongqing University, Chongqing 400045, China
Key Laboratory of New Technology for Construction of Cities in Mountain Area, Ministry of Education, Chongqing 400044, China
Chongqing Construction Investment (Group) Co., Ltd., Chongqing 400023, China
Keywords:
architectural concrete (AC), hyperparameter improvement, variable scale feature fusion, multi-volume algorithm comparison, bitmap data
Cite this article:
Yao G, Sun W, Yang Y, et al. Multi-volume variable scale bitmap data object classification algorithm architectural concrete color difference detection. Journal of Intelligent Construction, 2023, 1(2): 9180010. https://doi.org/10.26599/JIC.2023.9180010
Download citation
EndNote(RIS)
BibTeX

1481

Views

177

Downloads

Citations

2

Crossref

N/A

WoS

N/A

Scopus

N/A

CSCD

Abstract Full text About this article

Architectural concrete color difference (ACCD) directly affects building aesthetics. At present, the AC apparent quality detection method is based on a subjective artificial observation and detection process. The large volume of AC building, however, makes it difficult for quality inspectors to sample on site. Therefore, the manuscript establishes the aerial vehicle-to-ground coordinate conversion model and quadrotor unmanned aerial vehicle (QUAV) Eulerian motion model wherein the real-time optimization of QUAV motion parameters through remote sensing technology improves data collection stability. The proposed ACCD detection model, which is based on the QUAV remote sensing technology, is established by the improved multi-volume bitmap data object classification algorithm (BDOCA). The detection accuracy of MobileNetV3, ResNet50, and VGG16 algorithms reach 86.33%, 92.10%, and 87.62%, respectively. The study acquires experimental images from different buildings and produces a generalized identification set. It then verifies the ACCD detection model generalized identification capability by the traversal type detection method. The MobileNetV3, ResNet50, and VGG16 algorithms all achieved a generalized identification accuracy of 99.6%. The study builds the ACCD model by red-green-blue (RGB) spatial conversion, Kalman filtering noise reduction, noise point open operation, connected domain close operation, and mask quantization segmentation operation. This method implements color difference block coding, color difference threshold pixel point scale calculation, and geometric parameter calculation.


menu
Abstract
Full text
Outline
About this article

Multi-volume variable scale bitmap data object classification algorithm architectural concrete color difference detection

Show Author's information Gang Yao1,2, Wentong Sun1, Yang Yang1,2( ), Mingpu Wang1, Rui Li1, Yuanlin Zheng1,3
School of Civil Engineering, Chongqing University, Chongqing 400045, China
Key Laboratory of New Technology for Construction of Cities in Mountain Area, Ministry of Education, Chongqing 400044, China
Chongqing Construction Investment (Group) Co., Ltd., Chongqing 400023, China

Abstract

Architectural concrete color difference (ACCD) directly affects building aesthetics. At present, the AC apparent quality detection method is based on a subjective artificial observation and detection process. The large volume of AC building, however, makes it difficult for quality inspectors to sample on site. Therefore, the manuscript establishes the aerial vehicle-to-ground coordinate conversion model and quadrotor unmanned aerial vehicle (QUAV) Eulerian motion model wherein the real-time optimization of QUAV motion parameters through remote sensing technology improves data collection stability. The proposed ACCD detection model, which is based on the QUAV remote sensing technology, is established by the improved multi-volume bitmap data object classification algorithm (BDOCA). The detection accuracy of MobileNetV3, ResNet50, and VGG16 algorithms reach 86.33%, 92.10%, and 87.62%, respectively. The study acquires experimental images from different buildings and produces a generalized identification set. It then verifies the ACCD detection model generalized identification capability by the traversal type detection method. The MobileNetV3, ResNet50, and VGG16 algorithms all achieved a generalized identification accuracy of 99.6%. The study builds the ACCD model by red-green-blue (RGB) spatial conversion, Kalman filtering noise reduction, noise point open operation, connected domain close operation, and mask quantization segmentation operation. This method implements color difference block coding, color difference threshold pixel point scale calculation, and geometric parameter calculation.

Keywords: architectural concrete (AC), hyperparameter improvement, variable scale feature fusion, multi-volume algorithm comparison, bitmap data

References(43)

[1]

C. da Silva, F. Coelho, J. de Brito, et al. Statistical survey on inspection, diagnosis, and repair of architectural concrete surfaces. J Perform Constr Facil, 2017, 31: 04017097.
DOI Google Scholar
[2]

J. Miranda, J. Valença, H. Costa, et al. Chromatic design and application of restoration mortars on smooth surfaces of white and GRAY concrete. Struct Concr, 2021, 22: E535–E548.
DOI Google Scholar
[3]

T. A. Aiken, J. Kwasny, W. Sha, et al. Mechanical and durability properties of alkali-activated fly ash concrete with increasing slag content. Constr Build Mater, 2021, 301: 124330.
DOI Google Scholar
[4]

N. Goudjil, C. Djelal, Y. Vanhove, et al. Impact of temperature on the demoulding of concrete elements with a polarization process. Constr Build Mater, 2014, 54: 402–412.
DOI Google Scholar
[5]

K. Kalinowska-Wichrowska, E. Pawluczuk, M. Bołtryk, et al. The performance of concrete made with secondary products—Recycled coarse aggregates, recycled cement mortar, and fly ash–slag mix. Materials, 2022, 15: 1438.
DOI Google Scholar
[6]

M. K. Kim, J. P. P. Thedja, Q. Wang. Automated dimensional quality assessment for formwork and rebar of reinforced concrete components using 3D point cloud data. Autom Constr, 2020, 112: 103077.
DOI Google Scholar
[7]

P. Li, D. Wei, D. M. Zhang, et al. Study on the properties and mechanisms of a cement-stabilized aggregate mixture with vibration mixing. Front Mater, 2021, 8: 634336.
DOI Google Scholar
[8]

L. Libessart, P. de Caro, C. Djelal, et al. Correlation between adhesion energy of release agents on the formwork and demoulding performances. Constr Build Mater, 2015, 76: 130–139.
DOI Google Scholar
[9]

Y. Yang, H. C. Lu, X. K. Tan, et al. Fundamental mode shape estimation and element stiffness evaluation of girder bridges by using passing tractor-trailers. Mech Syst Signal Process, 2022, 169: 108746.
DOI Google Scholar
[10]

Y. Yang, Y. Ling, X. K. Tan, et al. Damage identification of frame structure based on approximate Metropolis–Hastings algorithm and probability density evolution method. Int J Struct Stab Dyn, 2022, 22: 2240014.
DOI Google Scholar
[11]

Y. Yang, J. L. Li, C. H. Zhou, et al. Damage detection of structures with parametric uncertainties based on fusion of statistical moments. J Sound Vib, 2019, 442: 200–219.
DOI Google Scholar
[12]

W. Z. Zhu, J. C. Gibbs, P. J. M. Bartos. Uniformity of in situ properties of self-compacting concrete in full-scale structural elements. Cem Concr Compos, 2001, 23: 57–64.
DOI Google Scholar
[13]

S. K. Rejeb. Improving compressive strength of concrete by a two-step mixing method. Cem Concr Res, 1996, 26: 585–592.
DOI Google Scholar
[14]

A. Brault, J. M. Lees. Wet casting of multiple mix horizontally layered concrete elements. Constr Build Mater, 2020, 247: 118514.
DOI Google Scholar
[15]

Y. Yang, Y. Zhang, X. K. Tan. Review on vibration-based structural health monitoring techniques and technical codes. Symmetry, 2021, 13: 1998.
DOI Google Scholar
[16]

K. Sotiriadis, P. Mácová, A. S. Mazur, et al. Long-term thaumasite sulfate attack on Portland-limestone cement concrete: A multi-technique analytical approach for assessing phase assemblage. Cem Concr Res, 2020, 130: 105995.
DOI Google Scholar
[17]

K. A. Mahmoud, O. L. Tashlykov, A. F. El Wakil, et al. Aggregates grain size and press rate dependence of the shielding parameters for some concretes. Prog Nucl Energy, 2020, 118: 103092.
DOI Google Scholar
[18]

H. J. Chen, N. H. Shih, C. H. Wu, et al. Effects of the loss on ignition of fly ash on the properties of high-volume fly ash concrete. Sustainability, 2019, 11: 2704.
DOI Google Scholar
[19]

H. Y. Xie, W. Shi, R. R. A. Issa, et al. Machine learning of concrete temperature development for quality control of field curing. J Comput Civ Eng, 2020, 34: 4020031.
DOI Google Scholar
[20]

S. Moon, B. Yang. Effective monitoring of the concrete pouring operation in an RFID-based environment. J Comput Civ Eng, 2010, 24: 108–116.
DOI Google Scholar
[21]

Y. Yang, Q. Cheng, Y. H. Zhu, et al. Feasibility study of tractor-test vehicle technique for practical structural condition assessment of beam-like bridge deck. Remote Sens, 2020, 12: 114.
DOI Google Scholar
[22]

L. Libessart, C. Djelal, P. de Caro, et al. Comparative study of the tribological behaviour of emulsions and demoulding oils at the concrete/formwork interface. Constr Build Mater, 2020, 239: 117826.
DOI Google Scholar
[23]

W. F. Price, S. J. Widdows. The effects of permeable formwork on the surface properties of concrete. Mag Concr Res, 1991, 43: 93–104.
DOI Google Scholar
[24]

A. R. Chen, Z. C. Pan, R. J. Ma. Mesoscopic simulation of steel rebar corrosion process in concrete and its damage to concrete cover. Struct Infrastruct Eng, 2017, 13: 478–493.
DOI Google Scholar
[25]

P. Soroushian, M. Elzafraney, A. Nossoni. Specimen preparation and image processing and analysis techniques for automated quantification of concrete microcracks and voids. Cem Concr Res, 2003, 33: 1949–1962.
DOI Google Scholar
[26]

C. Chateau, T. T. Nguyen, M. Bornert, et al. DVC-based image subtraction to detect microcracking in lightweight concrete. Strain, 2018, 54: e12276.
DOI Google Scholar
[27]

C. S. Cheng, Z. G. Shen. The application of gray-scale level-set method in segmentation of concrete deck delamination using infrared images. Constr Build Mater, 2020, 240: 117974.
DOI Google Scholar
[28]

B. J. Liu, T. Y. Yang. Image analysis for detection of bugholes on concrete surface. Constr Build Mater, 2017, 137: 432–440.
DOI Google Scholar
[29]

S. S. Tang, C. Ramseyer, P. Samant, et al. Erratum: “X-ray-induced acoustic computed tomography of concrete infrastructure” [Appl. Phys. Lett. 112, 063504 (2018)]. Appl Phys Lett, 2018, 112: 219901.
DOI Google Scholar
[30]

J. Q. Tao, H. T. Gong, F. Wang, et al. Automated image segmentation of air voids in hardened concrete surface using photometric stereo method. Int J Pavement Eng, 2022, 23: 5168–5185.
DOI Google Scholar
[31]

Z. Perkowski, K. Tatara. The use of Dijkstra’s algorithm in assessing the correctness of imaging brittle damage in concrete beams by means of ultrasonic transmission tomography. Materials, 2020, 13: 551.
DOI Google Scholar
[32]

L. Guo, R. Z. Li, B. Jiang, et al. Automatic crack distress classification from concrete surface images using a novel deep-width network architecture. Neurocomputing, 2020, 397: 383–392.
DOI Google Scholar
[33]

Y. J. Sun, Y. Yang, G. Yao, et al. Autonomous crack and bughole detection for concrete surface image based on deep learning. IEEE Access, 2021, 9: 85709–85720.
DOI Google Scholar
[34]

Z. Qu, J. Mei, L. Liu, et al. Crack detection of concrete pavement with cross-entropy loss function and improved VGG16 network model. IEEE Access, 2020, 8: 54564–54573.
DOI Google Scholar
[35]

S. M. Tang, Z. Q. Chen. Scale-space data augmentation for deep transfer learning of crack damage from small sized datasets. J Nondestr Eval, 2020, 39: 70.
DOI Google Scholar
[36]

C. Ding, Y. Li, L. Zhang, et al. Fast-convergent fully connected deep learning model using constrained nodes input. Neural Process Lett, 2019, 49: 995–1005.
DOI Google Scholar
[37]

A. Habib, J. Hasan, J. M. Kim. A lightweight deep learning-based approach for concrete crack characterization using acoustic emission signals. IEEE Access, 2021, 9: 104029–104050.
DOI Google Scholar
[38]

M. Kolla, T. VenuGopal. Semantic image clustering with global average pooled deep convolutional autoencoder. Helix, 2018, 8: 3561–3566.
DOI Google Scholar
[39]

Y. D. Yang, X. F. Wang, B. W. Sun, et al. Channel expansion convolutional network for image classification. IEEE Access, 2020, 8: 178414–178424.
DOI Google Scholar
[40]

F. J. Wei, G. Yao, Y. Yang, et al. Instance-level recognition and quantification for concrete surface bughole based on deep learning. Autom Constr, 2019, 107: 102920.
DOI Google Scholar
[41]

F. S. Bashiri, E. LaRose, P. Peissig, et al. Mcindoor20000: A fully-labeled image dataset to advance indoor objects detection. Data Brief, 2018, 17: 71–75.
DOI Google Scholar
[42]

I. Kandel, M. Castelli. The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset. ICT Express, 2020, 6: 312–315.
DOI Google Scholar
[43]

H. Iiduka. Appropriate learning rates of adaptive learning rate optimization algorithms for training deep neural networks. IEEE Trans Cybern, 2022, 52: 13250–13261.
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 22 February 2023
Revised: 23 May 2023
Accepted: 29 May 2023
Published: 21 July 2023
Issue date: June 2023

Copyright

© The Author(s) 2023. Published by Tsinghua University Press.

Acknowledgements

This research was funded by Research on Aerodynamic Characteristics and Vibration Suppression of Large-span Highway and Railway Suspension Bridges in Mountainous Cities (No. CQCT-JSA-GC-2021-0140), National Natural Science Foundation of China, “Intelligent Diagnosis of Service Safety of Major Infrastructures”, Topic III, “Multi-dimensional Characterization Index of Service Performance of Structures and its Intelligent Evaluation Theory and Method” (No. 52192663), and the project of “Basic Science of Intelligent Diagnosis and Treatment of Transportation Infrastructure Structure” under the “Engineering Science and Comprehensive Intersection” of the National Key Program of the 14th Five-Year Plan (No. 2021YFF0501000).

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Return