Classification and analysis of deep learning applications in construction: A systematic literature review

Khallaf, Rana; Khallaf, Mohamed

doi:10.1016/j.autcon.2021.103760

Cited by 93 publications

(38 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relevant literature is retrieved from the search engines based on their keywords and semantic search strings. The search strings are formed by using the keywords used in previous relevant literature reviews [5,18,19] and conceptual terms that are comparable. The keywords used for searching relevant papers include "crack detection" "deep learning", "crack detection" "Machine Learning", "crack detection" "road" "pavement" "concrete", "crack detection" "manual inspection", and "condition assessment" "computer vision" joined by Boolean operators "OR" as depicted in Table 1.…”

Section: Literature Retrievalmentioning

confidence: 99%

“…The capability and robustness of traditional approaches have been greatly extended by deep learning techniques [16]. In DL, the term "deep" refers to a large number of layers present between the input and the output layers [17][18][19]. DL models are different from traditional machine learning approaches in that they are capable of learning the representations of the data without introducing any hand-crafted rules or knowledge and have shown great performance in solving the crack detection problem [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

et al. 2022

View full text Add to dashboard Cite

The use of deep learning (DL) in civil inspection, especially in crack detection, has increased over the past years to ensure long-term structural safety and integrity. To achieve a better understanding of the research work on crack detection using DL approaches, this paper aims to provide a bibliometric analysis and review of the current literature on DL-based crack detection published between 2010 and 2022. The search from Web of Science (WoS) and Scopus, two widely accepted bibliographic databases, resulted in 165 articles published in top journals and conferences, showing the rapid increase in publications in this area since 2018. The evolution and state-of-the-art approaches to crack detection using deep learning are reviewed and analyzed based on datasets, network architecture, domain, and performance of each study. Overall, this review article stands as a reference for researchers working in the field of crack detection using deep learning techniques to achieve optimal precision and computational efficiency performance in light of electing the most effective combination of dataset characteristics and network architecture for each domain. Finally, the challenges, gaps, and future directions are provided to researchers to explore various solutions pertaining to (a) automatic recognition of crack type and severity, (b) dataset availability and suitability, (c) efficient data preprocessing techniques, (d) automatic labeling approaches for crack detection, (e) parameter tuning and optimization, (f) using 3D images and data fusion, (g) real-time crack detection, and (h) increasing segmentation accuracy at the pixel level.

show abstract

Section: Literature Retrievalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Recently, there has been an influx in publications of reviews and surveys that are concerned with the automation of the SHM process and the integration of ML. General applications of DL in construction are outlined in [21] and recent advances in computer vision methods including ML applied to the SHM process in [8], [22]. In [23]- [25] image processing methods exclusively for pavements including ML and DL are reviewed.…”

Section: Introductionmentioning

confidence: 99%

“…However, they also include a majority of the non-DL based ML methods. Whilst some other works like in [8], [21], [22], [24], [28], [29] include sections about DL methods for surface cracks, it is not a major focus, therefore, leaving out specific details about the different DL based approaches. Some works focus exclusively on surface cracks and DL [23], [25], [30].…”

Section: Introductionmentioning

confidence: 99%

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

König¹,

Jenkins²,

Mannion³

et al. 2022

Preprint

View full text Add to dashboard Cite

Surface cracks are a very common indicator of potential structural faults. Their early detection and monitoring is an important factor in structural health monitoring. Left untreated, they can grow in size over time and require expensive repairs or maintenance. With recent advances in computer vision and deep learning algorithms, the automatic detection and segmentation of cracks for this monitoring process have become a major topic of interest. This review aims to give researchers an overview of the published work within the field of crack analysis algorithms that make use of deep learning. It outlines the various tasks that are solved through applying computer vision algorithms to surface cracks in a structural health monitoring setting and also provides in-depth reviews of recent fully, semi and unsupervised approaches that perform crack classification, detection, segmentation and quantification. Additionally, this review also highlights popular datasets used for cracks and the metrics that are used to evaluate the performance of those algorithms. Finally, potential research gaps are outlined and further research directions are provided.

show abstract

“…2) Sample imbalance Nowadays, deep learning has been widely used in various fields, and many experiments have proven its reliability [17]- [20]. Image features can be extracted by convolution pooling, and image recognition and classification can be performed on this basis [21].…”

Section: Introductionmentioning

confidence: 99%

PSFNet: A Deep Learning Network for Fake Passport Detection

Jia

Lin

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Passport security feature classification has always been an important issue in border checks. Current manual methods struggle to achieve satisfactory results in terms of consistency and stability for security features with high similarity. For this reason, this study designs and develops a deep learningbased passport security feature classification model that can identify similar security features. The proposed model is based on the ShuffleNet v2, and its network structure is further optimized by two aspects for our task. Firstly, we embed pixel attention in the model to enable the network to better focus on important features with discriminatory power. Secondly, we introduce focal loss to relieve the overfitting problem caused by data imbalance. Finally, the superiority of the proposed classification algorithm is verified with the constructed passport security features data. The classification accuracy of the proposed algorithm is enhanced by 0.8%. The experimental results show that the classification accuracy is as high as 95.5%.INDEX TERMS Passport, security feature detection, deep learning.

show abstract

Classification and analysis of deep learning applications in construction: A systematic literature review

Cited by 93 publications

References 91 publications

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

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

PSFNet: A Deep Learning Network for Fake Passport Detection

Contact Info

Product

Resources

About