What's Cracking? A Review and Analysis of Deep Learning Methods for Structural Crack Segmentation, Detection and Quantification

König, Jacob; Jenkins, Mark A.; Mannion, Mike; Barrie, Peter; Morison, Gordon

doi:10.48550/arxiv.2202.03714

Cited by 2 publications

(2 citation statements)

References 120 publications

(258 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results indicate that DL crack identification does not rely on color, as grayscale models perform similarly to RGB models, thresholding, and edge detection models perform worse than RGB models. König et al (2022) discuss the importance of early surface crack detection and monitoring for structural health monitoring and provide a review of deep learning-based crack analysis algorithms. The study covers a range of tasks, including crack classification, detection, segmentation, and quantification, and offers thorough analyses of current fully, semi-, and unsupervised techniques.…”

Section: Prior Researchmentioning

confidence: 99%

Data-driven approach for AI-based crack detection: techniques, challenges, and future scope

Chakurkar,

Vora,

Patil

et al. 2023

Front. Sustain. Cities

View full text Add to dashboard Cite

This article provides a systematic literature review on the application of artificial intelligence (AI) technology for detecting cracks in civil infrastructure, which is a critical issue affecting the performance and longevity of these structures. Traditional crack detection methods involve manual inspection, which is laborious and time-consuming, especially in urban areas. Therefore, automatic crack detection with AI technology has gained popularity due to its ability to identify degradation of roads in real-time, leading to increased safety and reliability. This review emphasizes two key approaches for crack detection: deep learning and traditional computer vision, with a focus on data-driven aspects that rely primarily on data from training datasets to detect and quantify the severity level of the crack. The article highlights the advantages and drawbacks of each approach and provides an overview of various crack detection models, feature extraction techniques, datasets, potential issues, and future directions. The research concludes that deep learning-based methods used for crack classification, localization and segmentation have shown better performance than traditional computer vision techniques, especially in terms of accuracy. However, deep learning methods require large amounts of training data and computational power, which can be a significant limitation. Additionally, the article identifies a lack of 3D datasets, unsupervised learning algorithms are rarely used to train crack detection model, and datasets having road images with variety of road textures such as asphalt and cement etc. as challenges for future research in this field. A need for 3D and combined texture datasets as challenges for future research in this field.

show abstract

Section: Prior Researchmentioning

confidence: 99%

Data-driven approach for AI-based crack detection: techniques, challenges, and future scope

Chakurkar,

Vora,

Patil

et al. 2023

Front. Sustain. Cities

View full text Add to dashboard Cite

show abstract

“…Various metrics were used to evaluate the network, such as accuracy, precision, sensitivity and specificity (König et al, 2022). This metrics are explained in more detail below.…”

Section: Network Training Validation and Testingmentioning

confidence: 99%

Deep machine learning in bridge structures durability analysis

Tomaszkiewicz

Owerko

2022

Proceedings of the 5th Joint International Symposium on Deformation Monitoring - JISDM 2022

View full text Add to dashboard Cite

According to Eurocode 0 structural durability is next to ultimate and serviceability one of the basic criteria in the structural design process. This article discusses the subject of concrete cracks observation in bridge structures, as one of the factors determining their durability. The durability of bridge structures is important due to both social, economic aspects and also the defense aspects of countries. Cracking of the reinforced concrete structures is a natural effect in concrete. The aim in the design and construction of structures is not to prevent the formation of cracks, but to limit their width to acceptable values. At the same time, there is a need for structure tests that allow for non-contact, fast measurements and algorithms that allow for efficient analysis of large amounts of measurement data. Deep machine learning algorithms can be used here. They can be used to analyse data which are acquired by means of photogrammetric methods (especially helpful during construction to inventory concealed works). Moreover, they can also be applied to standard data acquisition methods, consisting in photographing objects damage during works acceptance or periodic inspections. This paper discusses the application of deep machine learning to assess the condition of bridge structures based on photographs of object damage. The use of this method makes it possible to observe the rate and extent of damage development. Consequently, this method makes it possible to predict the development of damage in time and space in order to prevent failures and take structures out of service.

show abstract

What's Cracking? A Review and Analysis of Deep Learning Methods for Structural Crack Segmentation, Detection and Quantification

Cited by 2 publications

References 120 publications

Data-driven approach for AI-based crack detection: techniques, challenges, and future scope

Data-driven approach for AI-based crack detection: techniques, challenges, and future scope

Deep machine learning in bridge structures durability analysis

Contact Info

Product

Resources

About