Article
Engineering, Multidisciplinary
Bei Zhang, Haoyuan Cheng, Yanhui Zhong, Xianghua Tao, Guanghui Li, Shengjie Xu
Summary: This paper proposes a method based on feature pixel points to quantify and calculate the vertical height of concealed cracks in asphalt pavements. By conducting numerical simulations, the characteristics of ground-penetrating radar (GPR) images of concealed cracks in asphalt pavement with varying lengths and widths were studied. The relationship between the pixel value of the crack area and the two-way travel time was established to obtain the relationship between the vertical height of the crack and the pixel. This method achieved a minimum error of only 2.9% in estimating the vertical height of cracks and can be applied in practical engineering applications.
Article
Environmental Sciences
Xuan Lin, Jian Zhang, Daifeng Wu, Enhong Meng, Maoyi Liu, Meng Li, Fuliu Gao
Summary: The identification of pavement cracks is crucial for road safety, but manual detection is time-consuming. An automated technology is needed, however, automatic crack recognition is challenging due to crack intensity heterogeneity and complex backdrops. To address this, a new network architecture called PSA-Net is proposed, which combines feature pyramid and attention mechanism. The effectiveness of the proposed technique is verified using a dataset of real road cracks and compared with different crack detection methods.
FRONTIERS IN ENVIRONMENTAL SCIENCE
(2023)
Review
Construction & Building Technology
Lu Lu, Deying Zhao, Jizhou Fan, Guoqiang Li
Summary: Pavement is crucial in modern society and requires proper sealant to prevent water penetration and premature structural failure. This paper reviewed various types of sealants for cement concrete pavement and discussed new developments such as shape memory polymers used as sealants, concluding with future perspectives.
ROAD MATERIALS AND PAVEMENT DESIGN
(2022)
Article
Chemistry, Multidisciplinary
Zhaomeng Zhou, Sijie Cai, Bingjing Lin, Jianchun Lin
Summary: This paper proposes an intelligent pavement crack detection and repair algorithm to improve the efficiency and reduce the labor cost of pavement repair. The algorithm uses image numerical parameters to classify cracks with different geometric features and extracts texture geometric features of various types of cracks based on different filtering strategies. Finally, the algorithm establishes a mathematical model for efficient trajectory planning combined with the nozzle size of the crack-repairing machine.
APPLIED SCIENCES-BASEL
(2023)
Article
Multidisciplinary Sciences
Zhihan Lv, Chen Cheng, Haibin Lv
Summary: This study aims to improve the efficiency of automatic identification of pavement distress and address the challenges in identifying and detecting pavement distress. It analyzes the identification method and types of pavement distress, describes the design concept of deep learning in pavement distress recognition, and applies the Mask R-CNN model in road crack distress recognition. The results show high accuracy in the model's recognition performance and different crack detection methods, providing valuable insights for the application of deep CNNs in pavement distress recognition and contributing to the improvement of road traffic conditions for smart cities in the future.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2023)
Article
Construction & Building Technology
Shuwei Li, Xingyu Gu, Xiangrong Xu, Dawei Xu, Tianjie Zhang, Zhen Liu, Qiao Dong
Summary: This study introduces an effective method utilizing 3-D ground penetrating radar (GPR) and deep learning models to automatically detect concealed cracks in asphalt pavement. The results demonstrate the feasibility of the proposed method, with YOLOv4 and YOLOv5 models showing significant advancements in crack detection even with a small dataset.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Computer Science, Interdisciplinary Applications
A. Diana Andrushia, N. Anand, G. Prince Arulraj
Summary: The study proposed a method for thermal crack detection using Ripplet transform, including steps like noise removal, image enhancement, crack detection and detection of crack geometric parameters. The geometric parameters of the cracks were quantified through length, width, perimeter and area to identify the thermal cracks. The results were compared with other transform domain based methods.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2021)
Article
Construction & Building Technology
Frank K. A. Awuah, Alvaro Garcia-Hernandez
Summary: This paper demonstrates a machine process for repairing cracks in asphalt pavements using hot bitumen filling for the first time. The researchers characterized the quality of the fillings and examined how various factors affect the filling quality. The study showed that bitumen flow, filling speed, and crack dimensions determine the quality of the filling and will require careful control in future autonomous crack filling devices.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Chemistry, Multidisciplinary
Yongshang Li, Nan Yang
Summary: This study proposes methods for image feature enhancement and crack identification of asphalt concrete pavement cracks, which can provide help for pavement maintenance. The experiment found that this method can effectively remove noise information from asphalt concrete crack images, improve the image entropy value, and achieve accurate identification of crack distribution direction, length, and width. The method has high identification efficiency and good application effect.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Hardware & Architecture
Jongwoo Ha, Dongsoo Kim, Minsoo Kim
Summary: This study proposed a system that can automatically detect, classify, and assess the severity of road cracks by expanding the number of crack types and including crack severity assessment, achieving an accuracy of 91.2% for both crack type and severity assessment.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Construction & Building Technology
Ganesh Kolappan Geetha, Sung-Han Sim
Summary: This paper presents a computationally efficient deep learning model for real-time classification of concrete crack/non-crack. It also investigates the 'black-box' nature of the model using explainable artificial intelligence. The proposed framework combines image binarization and a Fourier-based 1D deep learning model for fast detection and classification of concrete crack/non-crack features. The model enables real-time pixel-level classification at a rate of 2 images per second on a mobile platform with limited computational resources.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Chemistry, Analytical
Souhir Sghaier, Moez Krichen, Imed Ben Dhaou, Hela Elmannai, Reem Alkanhel
Summary: Advances in technology have allowed the development of automated inspection systems for road cracks, but the identification process is still in its early stages due to challenges in obtaining pavement photographs and the small size of cracks. The existence of cracks reduces the value of infrastructure, making the estimation of fracture severity crucial. This work aims to create an efficient automated system for crack identification, extraction, and 3D reconstruction to prevent traffic deaths and improve road safety.
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
Chemistry, Multidisciplinary
Nan Yang, Yongshang Li, Ronggui Ma
Summary: This study addresses the problem of efficiently detecting cracks and sealed cracks in asphalt pavements through the use of deep learning. It creates a dataset, develops crack annotation methods, and conducts experiments to achieve efficient and accurate crack detection.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Multidisciplinary
Li Song, Hongshuo Sun, Jinliang Liu, Zhiwu Yu, Chenxing Cui
Summary: The article introduces a method for automatic detection and quantification of cracks on concrete structure surfaces. The method uses an electric driving platform for close-range scanning and shooting, applies convolutional neural networks for automatic segmentation, and employs crack matching and property calculation methods for automatic quantification. Experimental results demonstrate high accuracy of the method.