Review
Construction & Building Technology
Jianghua Deng, Amardeep Singh, Yiyi Zhou, Ye Lu, Vincent Cheng-Siong Lee
Summary: This review provides a comprehensive overview of the latest advancements in computer vision-based crack analysis for civil infrastructure, covering both qualitative and quantitative aspects, particularly focusing on image processing and deep learning-based methodologies from image-level detection to pixel-level segmentation and quantification. The challenges and research gaps are also discussed, highlighting the importance of future research in this field.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Amir Hossein Asjodi, Mohammad Javad Daeizadeh, Mohammadjavad Hamidia, Kiarash M. Dolatshahi
Summary: A new image-based method called the Arc Length method is introduced for accurately extracting crack width and length, showing high efficiency in crack monitoring in laboratory experiments. The method has significant potential applications in crack monitoring of infrastructures like concrete bridges and tunnels.
STRUCTURAL CONTROL & HEALTH MONITORING
(2021)
Article
Environmental Sciences
Haitao Yu, Zhibin Liu, Yun Zhang, Tingyi Luo, Yasen Tang
Summary: This study analyzed three fault samples from a mining area in Southwest Shandong, China, and found significant positive correlations among the geometric characteristic parameters, while the nonuniformity coefficient is positively correlated with the parameters of the crack network. The crack extension forms of different fault rock samples are related to the fracture toughness of mineral particles. Additionally, it was observed that crack networks are most developed in samples with the least clay content, and there is a negative correlation between clay content and the geometric parameters of the crack network.
ENVIRONMENTAL EARTH SCIENCES
(2022)
Article
Engineering, Geological
Jie Liu, Jincheng Huang, Keyu Liu, Klaus Regenauer-Lieb
Summary: Characterizing cracks in 3D space requires several processing steps, including pre-processing, segmentation, analysis, filtering, smoothing, thinning, separating, and labeling. Extracting statistical variables and defining the scaling law of cracks is possible once detailed characteristics of individual cracks in a 3D system are documented.
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2021)
Article
Construction & Building Technology
Tibebe Tesfaye Yalew, Ki-Seong Kim
Summary: This study proposes an image processing method that enhances crack detection by utilizing variance-based image enhancement, polynomial curve fit noise detrend technique, symmetry and geometric-based filtration, and trajectory-based local binarization. The algorithm is effective in detecting and sizing cracks, as validated by testing on 80 real images.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Construction & Building Technology
Lu Deng, Tao Sun, Liang Yang, Ran Cao
Summary: This paper presents an automated 3D reconstruction and length quantification framework for cracks in concrete structures based on binocular videos. A crack semantic 3D reconstruction method combined with binocular visual simultaneous localization and mapping (VSLAM) and a high-performance segmentation network is proposed to achieve accurate crack 3D characterization and global localization. A 3D crack quantification method based on point cloud processing is also developed to accurately identify individual cracks on the global structure and quantify their lengths. Field tests on a concrete bridge demonstrate the high efficiency and practicability of the proposed automated inspection framework, and the accuracy of crack detection and quantification is validated against manual inspection results.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Engineering, Civil
Xiong Peng, Kun Zhou, Bingxu Duan, Xingu Zhong, Chao Zhao, Tianyu Zhang
Summary: In this paper, a fast and simplified crack width quantification method is proposed using deep Q learning and geometric calculation. The crack edge is extracted using U-Net network and edge detection operator, and the intelligent decision is made by the deep Q learning model. Additionally, a geometric calculation method based on endpoint and curvature extreme point detection is introduced. The proposed method achieves high precision in quantifying the real crack width.
SMART STRUCTURES AND SYSTEMS
(2023)
Article
Engineering, Civil
Nicola Gehri, Jaime Mata-Falcon, Walter Kaufmann
Summary: This paper presents important refinements to the automatic crack detection and measurement procedure based on DIC surface displacement measurements. The refinements include a Canny edge-based crack detector and enhancements in crack kinematic measurement. Validation tests show improved reliability in detecting thinner cracks with accurate crack kinematic measurements in large-scale experiments.
ENGINEERING STRUCTURES
(2022)
Article
Engineering, Mechanical
Shaofeng Wang, Lianshuai Zhang, Yu Qian, Yu Zhou
Summary: Rail head spalling and fractures are closely associated with fatigue crack propagation. This study aims to accurately capture the true three-dimensional shape of fatigue cracks during initiation and propagation. New mathematical and physical models based on reconstructed 3D cracks are proposed to predict rail crack propagation at different service stages. The analysis reveals that the crack propagation path in the 2D lateral rail section approximates a quadratic parabola or circular curve, while the 3D crack morphology resembles a partial spherical surface with a curvature radius of approximately 18.5 mm. The proposed reconstruction model can predict internal crack propagation on the rail head surface, aiding in track inspection, maintenance, and repair.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Chemistry, Multidisciplinary
Mthabisi Adriano Nyathi, Jiping Bai, Ian David Wilson
Summary: This paper proposes a novel image-based method for measuring concrete crack width using a laser beam and image processing. The method was validated in the laboratory and showed high accuracy and practicality.
APPLIED SCIENCES-BASEL
(2023)
Article
Construction & Building Technology
Pengyong Miao, Teeranai Srimahachota
Summary: This study proposed a semi-automated system for crack detection and quantification, using a trained CNN and an application. GoogLeNet was determined as the CNN model for the study, with transfer learning showing balanced performances on two datasets. The study introduced a new sliding window technique and crack width calculation method, and developed an application integrating these methods to detect and analyze cracks effectively.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Engineering, Civil
Eunbyul Koh, Seung-Seop Jin, Robin Eunju
Summary: This study presents an image processing procedure that accurately detects cracks and classifies different types of cracks in concrete structures. The algorithm has been developed using field-obtained images and validated with an additional 227 images from an open database, achieving an average accuracy of 92.8% in the test datasets.
SMART STRUCTURES AND SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Gang Li, Yongqiang Chen, Jian Zhou, Xuan Zheng, Xue Li
Summary: This study proposed a new road crack detection method using a matrix network combined with corner-based detection and segmentation network to improve crack identification. Experimental results showed that the detection performance of this method is better than various other algorithms and has strong anti-interference ability.
ENGINEERING COMPUTATIONS
(2022)
Article
Materials Science, Composites
Christopher S. Meyer, Enock Bonyi, Kyle Drake, Taofeek Obafemi-Babatunde, Aimanosi Daodu, Demilade Ajifa, Amber Bigio, Justin Taylor, Bazle Z. (Gama) Haque, Daniel J. O'Brien, John W. Gillespie, Kadir Aslan
Summary: This study developed automated methods for identifying and quantifying transverse matrix crack damage on the surface of composites. By using model specimens and high-resolution image capture, two automated methods were developed to identify and quantify transverse cracks.
JOURNAL OF REINFORCED PLASTICS AND COMPOSITES
(2021)
Article
Chemistry, Analytical
Chien-Sheng Liu, Ho-Da Tu
Summary: In this study, a novel algorithm was developed to quickly calculate the ideal center of elliptical spots in autofocus microscopes, improving the autofocusing accuracy to less than 1.5 μm. The proposed algorithm effectively compensates for the linearity of the focusing characteristic curve, enhancing the image processing capabilities in optics-based autofocusing microscopes.
Article
Environmental Sciences
Hao Zeng, Chao-Sheng Tang, Cheng Zhu, Qing Cheng, Zong-ze Lin, Bin Shi
Summary: Soil desiccation cracking is a significant concern in various fields, and this study utilizes infrared thermal imaging to investigate the correlation between soil temperature and cracking behaviors, providing insights into the underlying mechanisms of soil cracking.
WATER RESOURCES RESEARCH
(2022)
Article
Environmental Sciences
Chun Liu, Bin Shi, Kai Gu, Tiansheng Zhang, Chaosheng Tang, Yue Wang, Suping Liu
Summary: Recent findings suggest that land subsidence in the south Yangtze River delta area has not ceased despite the rise in groundwater levels. Laboratory tests and simulations have revealed significant compressive strain in the aquitard above the exploited aquifer, which is influenced by the negative pore water pressure. This highlights the potential compression of aquitards during draining and recharging cycles.
WATER RESOURCES RESEARCH
(2022)
Article
Environmental Sciences
Zhu-Yuan Lin, Chao-Sheng Tang, Zhan-Ming Yang, Yi-Shu Wang, Qing Cheng, Bin Shi
Summary: In this study, drying-induced soil curling phenomenon was investigated through experiments and modeling. The variation in moisture gradient was found to be a crucial factor contributing to the curling.
WATER RESOURCES RESEARCH
(2022)
Article
Engineering, Geological
Chao-Sheng Tang, Xue-Peng Gong, Zhengtao Shen, Qing Cheng, Hilary Inyang, Chao Lv, Bin Shi
Summary: Rainfall infiltration is a key factor in geological hazards, ecological environment problems, and engineering accidents. This study investigates the process of soil wetting during rainfall infiltration and its impact on soil mechanical properties through micro-penetration tests and moisture monitoring. The results show that as infiltration time increases, the wetting front moves downward and the range widens. The penetration resistance varies at different depths. The study also finds that the evolution of soil mechanical characteristics is influenced by the redistribution of water content along depth. The method of micro-penetration proves feasible for studying rainfall infiltration and wetting process in surface soil layer or laboratory small-scale soil samples.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2022)
Article
Engineering, Geological
Jin-Jian Xu, Chao-Sheng Tang, Qing Cheng, Farshid Vahedifard, Bo Liu, Bin Shi
Summary: This study presents a novel framework for monitoring and early detecting soil cracking using distributed fibre optical sensing (DFOS) technique. The results reveal a strong correlation between soil strain and crack evolution, confirming the efficacy and reliability of the proposed framework. Compared to traditional strain monitoring methods, DFOS-OFDR offers higher accuracy and continuous monitoring.
Review
Engineering, Geological
Chao-Sheng Tang, Qing Cheng, Xuepeng Gong, Bin Shi, Hilary I. Inyang
Summary: Variability in moisture content significantly influences soil properties. Understanding the soil microstructure evolution during wetting/drying process is crucial for interpreting soil macro hydro-mechanical behavior. This review summarizes commonly used methods and research progress in studying soil microstructure, and proposes important research areas for future work.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2023)
Article
Engineering, Geological
Chao Lv, Chao-Sheng Tang, Cheng Zhu, Wei-Qiang Li, Tian-Yu Chen, Liang Zhao, Xiao-Hua Pan
Summary: Microbial-induced calcium carbonate precipitation (MICP) is an eco-friendly technique with promising applications. This study investigates the effects of temperature, pH, bacteria and cementation solution concentration on the mineral compositions and cementitious characteristics of calcium carbonate precipitations. The results demonstrate the strong dependence of calcium carbonate precipitations on these factors.
JOURNAL OF GEOTECHNICAL AND GEOENVIRONMENTAL ENGINEERING
(2022)
Article
Engineering, Geological
Rui Wang, Chao-Sheng Tang, Xiao-Hua Pan, Dian-Long Wang, Zhi-Hao Dong, Bin Shi
Summary: The bio-carbonation method using reactive magnesia cement (RMC) was proven to be effective for stabilizing dredged sludge with high initial water content. The stabilization performance was influenced by curing agent components, bacteria concentration, and urea content. The combination of brucite and bio-carbonation products of RMC played a significant role in improving the physico-mechanical properties of the dredged sludge.
Article
Engineering, Geological
Chao Lv, Chao-Sheng Tang, Jun-Zheng Zhang, Xiao-Hua Pan, Hao Liu
Summary: This study investigates the optimized design of bio-mediated soil enhancement and examines the influence of different calcium sources and magnesium ion concentrations on the treatment of calcareous sand using microbially induced carbonate precipitation (MICP) technique. The experimental results show that the type of calcium source affects the mechanical strength and carbonate content of the bio-cemented samples, while the addition of magnesium ions enhances their strength. SEM and XRD analysis indicate that the morphological features and mineral compositions of carbonate precipitations are strongly dependent on calcium source and magnesium ion concentration.
Article
Engineering, Geological
Qing Cheng, Ying-Dong Gu, Chao-Sheng Tang, Xi-Ying Zhang, Bin Shi
Summary: Vegetation is commonly used in geotechnical engineering, but the problem of desiccation cracking in vegetated soils is often overlooked. This study investigates the behavior of desiccation cracking in a vegetated soil with different planting densities. The results show that as the planting density increases, more crack initiation points are observed and the cracking water content decreases. In addition, the crack ratio and average crack width of the vegetated samples are smaller than those of the bare soil sample. An appropriate planting density is necessary to effectively inhibit soil desiccation cracking.
CANADIAN GEOTECHNICAL JOURNAL
(2023)
Article
Engineering, Civil
Shaini Aluthgun Hewage, Kaniz Roksana, Chao Sheng Tang, Zhuang Zhuo, Cheng Zhu
Summary: This study investigates the influence of wood biochar dosages on surface cracking under freeze-thaw cycles on clayey soils and explores the mechanism through image analysis and water evaporation. The results show that increased dosage of biochar reduces crack parameters and crack propagation rate, while also decreasing water evaporation rate. The final crack patterns are found to be associated with the initial ice crystal patterns.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Environmental
Jun-Zheng Zhang, Chao-Sheng Tang, Cheng Zhu, Qi-You Zhou, Jin-Jian Xu, Bin Shi
Summary: This study presents a novel ERT-based method to characterize and quantify clayey soil desiccation cracking. The results show that ERT can effectively capture and image the cracking process, and the estimated cracking depths using ERT are consistent with experimental observation.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhao-Jun Zeng, Chao-Sheng Tang, Qing Cheng, Ni An, Xiao-Ying Chen, Bin Shi
Summary: In this study, a new numerical approach is proposed to simulate water evaporation in cracked soils, which divides the cracked soil into soil and air domains and determines the boundary conditions using vapor flux. Numerical tests show that air humidity and segmentation method affect the soil evaporation rate and volumetric water content profile. The results indicate that soil water content near soil and crack surfaces decreases more rapidly and air humidity influences the evaporation rate.
COMPUTERS AND GEOTECHNICS
(2023)
Article
Soil Science
Jun-Yi Guo, Bin Shi, Meng-Ya Sun, Cheng-Cheng Zhang, Chao-Sheng Tang, Guang-Qing Wei, Jin-Hui Fang, Hong-Tao Jiang
Summary: This research presents a novel fiber-optic suction sensor for measuring the suction of water in unsaturated soils. Experimental results show that the sensor has a wide measurement range, small error, and can effectively capture various data in the soil.
Article
Engineering, Geological
Dian-Long Wang, Chao-Sheng Tang, Xiao-Hua Pan, Rui Wang, Min Shi, Zhi-Hao Dong, Yi-Cheng Zhang, Bin Shi
Summary: This study proposes a novel bio-carbonation method using urea pre-hydrolysis to stabilize geomaterial with reactive magnesia cement (RMC). The pre-hydrolysis of urea in the bacterial solution enhances the RMC bio-carbonation reaction, resulting in the formation of more hydrated magnesia carbonates (HMCs) that contribute to strength gain. The study investigates the effect of urea pre-hydrolysis on the engineering performance of bio-carbonated samples and provides insights for the design of bio-carbonated RMC in field applications.
Article
Computer Science, Interdisciplinary Applications
Yapo Abole Serge Innocent Oboue, Yunfeng Chen, Sergey Fomel, Wei Zhong, Yangkang Chen
Summary: Strong noise can disrupt the recorded seismic waves and negatively impact subsequent seismological processes. To improve the signal-to-noise ratio (S/N) of seismological data, we introduce MATamf, an open-source MATLAB code package based on an advanced median filter (AMF) that simultaneously attenuates various types of noise and improves S/N. Experimental results demonstrate the usefulness and advantages of the proposed AMF workflow in enhancing the S/N of a wide range of seismological applications.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Upkar Singh, P. N. Vinayachandran, Vijay Natarajan
Summary: The Bay of Bengal maintains its salinity distribution due to the cyclic flow of high salinity water and the mixing with freshwater. This paper introduces an advection-based feature definition and algorithms to track the movement of high salinity water, validated through comparison with observed data.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Bijal Chudasama, Nikolas Ovaskainen, Jonne Tamminen, Nicklas Nordback, Jon Engstro, Ismo Aaltonen
Summary: This contribution presents a novel U-Net convolutional neural network (CNN)-based workflow for automated mapping of bedrock fracture traces from aerial photographs acquired by unmanned aerial vehicles (UAV). The workflow includes training a U-Net CNN using a small subset of photographs with manually traced fractures, semantic segmentation of input images, pixel-wise identification of fracture traces, ridge detection algorithm and vectorization. The results show the effectiveness and accuracy of the workflow in automated mapping of bedrock fracture traces.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Ruizhen Wang, Siyang Wan, Weitao Chen, Xuwen Qin, Guo Zhang, Lizhe Wang
Summary: This paper proposes a novel framework to generate a finer soil strength map based on RCI, which uses ensemble learning models to obtain USCS soil classification and predict soil moisture, in order to improve the resolution and reliability of existing soil strength maps.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Zhanlong Chen, Xiaochuan Ma, Houpu Li, Xuwei Xu, Xiaoyi Han
Summary: Simulated terrains are important for landform and terrain research, disaster prediction, rescue and disaster relief, and national security. This study proposes a deep learning method, IGPN, that integrates global information and pattern features of the local terrain to generate accurate simulated terrains quickly.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Daniele Secci, Vanessa A. Godoy, J. Jaime Gomez-Hernandez
Summary: Neural networks excel in various machine learning applications, but lack physical interpretability and constraints, limiting their accuracy and reliability in predicting complex physical systems' behavior. Physics-Informed Neural Networks (PINNs) integrate neural networks with physical laws, providing an effective tool for solving physical problems. This article explores recent developments in PINNs, emphasizing their application in solving unconfined groundwater flow, and discusses challenges and opportunities in this field.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Renguang Zuo, Ying Xu
Summary: This study proposes a hybrid deep learning model consisting of a one-dimensional convolutional neural network (1DCNN) and a graph convolutional network (GCN) to extract joint spectrum-spatial features from geochemical survey data for mineral exploration. The physically constrained hybrid model performs better in geochemical anomaly recognition compared to other models.
COMPUTERS & GEOSCIENCES
(2024)