A real-time crack detection algorithm for pavement based on CNN with multiple feature layers

Ma, Duo; Fang, Hongyuan; Wang, Niannian; Xue, Binghan; Dong, Jiaxiu; Wang, Fu

doi:10.1080/14680629.2021.1925578

Cited by 35 publications

(19 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of the input images that converted from the captured video can be calculated as 2390 s Â 24FPS = 57,360. According to the testing time of the textbook examples mentioned in Section 3.1, and the study outcomes of [28], the time of CNN processing is around 100 images per second. Then, the time of CNN processing can be calculated as 57,360/100 = 573.6 s. Therefore, the cost of computer-vision based crack inspection can be calculated as (2390 s + 573.6 s) Â (85.9/3600) = $70.7.…”

Section: Comparison Of Cnn and Manual Inspectionmentioning

confidence: 99%

Computer Vision-Based Techniques for Quality Inspection of Concrete Building Structures

Chang¹,

Siu²

2023

Quality Control - An Anthology of Cases

View full text Add to dashboard Cite

Quality performance of building construction is frequently assessed throughout the construction life cycle. In Hong Kong, quality management system must be established before commencing new building works. Regular building inspections are conducted in accordance with the code of practice of new building works. Quality managers are deployed in construction sites to inspect and record any building defects. The concrete cracks must be identified, which is usually followed by proposed rectifications, in order to protect the public and occupants from dangers. This chapter is structured as follows: Background information of concrete cracks is firstly given. Traditional technique of conducting regular manual inspection is introduced, in accordance with Hong Kong’s code of practice “Building Performance Assessment Scoring System (PASS)”. Then, an advanced technique of conducting crack inspection intelligently based on computer vision is introduced. The procedures of defining, training, and benchmarking the architecture of convolutional neural network models are presented. The calculation steps are detailed and illustrated using a simple textbook example. An experiment case study is used to compare the time, cost of inspecting concrete cracks using both manual and advanced technique. The study concludes with a presentation of the future vision of robot-human collaboration for inspecting concrete cracks in building construction.

show abstract

Section: Comparison Of Cnn and Manual Inspectionmentioning

confidence: 99%

Computer Vision-Based Techniques for Quality Inspection of Concrete Building Structures

Chang¹,

Siu²

2023

Quality Control - An Anthology of Cases

View full text Add to dashboard Cite

show abstract

“…In most of the retrieved literature, efforts of crack detection are mainly dedicated to the geometric feature extraction, classification, and severity evaluation of the surface cracks in the pavement structure. It is the periodical monitoring of macro crack propagation, which belongs to the external observation and the research findings which have been published relatively more (Al-Qadi et al, 2010;Ma et al, 2022;Sun et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Pavement Crack Monitoring: Literature Review

Fahad¹,

Nagy²,

Guangpin³

et al. 2023

IJCE

View full text Add to dashboard Cite

Crack monitoring of pavements is an ever-evolving technology with new crack identification technologies being introduced frequently. Although older technologies consisted of physical removing the pavement section using coring, however new methods are available that are non-destructive and yield a higher performance than conventional technologies. This paper compiles various crack monitoring technologies such as wireless sensor networks, photo imaging, laser imaging, 3D road surface profile scans, acoustics wave propagation technology, embedded strain sensors and onboard vehicle sensors that majorly use an artificial intelligence algorithm to identify and categorize the cracks. The research also includes the use of convolutional neural network that can be used to analyze pavement images and such neural network can localize and classify the cracks for crack initiation and propagation stage. The research concludes with the favor of using the optical imaging technology called Syncrack which serves better performance in terms of time of prediction by 25% and accuracy by 30% when compared to other sensing technologies.

show abstract

“…Xu et al, [ 28 ] aimed to assess pavement damage by extracting cracks and potholes, classifying them from vision. Due to their better generalization and portability, convolutional neural networks (CNNs) have been gradually applied to extract crack features in combination with image processing methods [ 29 ]. Sholevar et al, [ 30 ] proposed a deep convolutional neural network (CNN) as a detection system for asphalt pavement cracks, which is capable of robust detection and classification of pavement cracks.…”

Section: Introductionmentioning

confidence: 99%

Automatic Pavement Defect Detection and Classification Using RGB-Thermal Images Based on Hierarchical Residual Attention Network

Chen

Chandra

Seo

2022

Sensors

View full text Add to dashboard Cite

A convolutional neural network based on an improved residual structure is proposed to implement a lightweight classification model for the recognition of complex pavement conditions, which uses RGB-thermal as input and embeds an attention module to adjust the spatial, as well as channel, information of the images. The best prediction accuracy of the proposed model is 98.88%, while the RGB-thermal is used as input and an attention mechanism is used. The attention mechanism increases the attention to detail of the image and regulates the use of image channels, which enhances the final performance of the model. It is also compared with state-of-the-art (SOTA) deep learning models, indicating our model has fewer parameters, shorter training time, and higher recognition accuracy compared to existing image classification models. A visualization method incorporating gradient-weighted class activation mapping (Grad-CAM) is proposed to analyze the classification results, comparing the data the model learns from the images under different input data.

show abstract

A real-time crack detection algorithm for pavement based on CNN with multiple feature layers

Cited by 35 publications

References 31 publications

Computer Vision-Based Techniques for Quality Inspection of Concrete Building Structures

Computer Vision-Based Techniques for Quality Inspection of Concrete Building Structures

Pavement Crack Monitoring: Literature Review

Automatic Pavement Defect Detection and Classification Using RGB-Thermal Images Based on Hierarchical Residual Attention Network

Contact Info

Product

Resources

About