Image-based concrete crack detection in tunnels using deep fully convolutional networks

Ren, Yupeng; Huang, Jisheng; Hong, Zhiyou; Lü, Wei; Yin, Jianqin; Zou, Lejun; Shen, Xiaohua

doi:10.1016/j.conbuildmat.2019.117367

Cited by 321 publications

(173 citation statements)

References 29 publications

Supporting

Mentioning

141

Contrasting

Unclassified

Order By: Relevance

“…The idea of this preliminary study is to investigate the generalization capability of a U-Net based segmentation model trained using a small labeled dataset and tested on a large set of unseen imagery depicting cracks in concrete materials. Specifically, the deep fully CNN, named CrackSegNet (Ren et al, 2020), was adopted to perform a pixel-level classification of cracks. CrackSegNet is an end-to-end crack detection architecture that combines backbone network, dilated convolution, spatial pyramid pooling and skip connection modules to detect cracks.…”

Section: Preliminary Results On Crack Segmentationmentioning

confidence: 99%

“…Two different datasets were used in this study. The first one, provided by Ren et al (Ren et al, 2020), includes a total of 409 RGB images of cracks (4032 × 3016 pixels) acquired in a tunnel under different light conditions and then cropped into 919 small images (512 × 512 pixels). The small images are divided into a training set and a test set at a ratio of 4 : 1.…”

Section: Datasetsmentioning

confidence: 99%

“…Among the developed methods for crack detection, edge-detection algorithms (Abdel-Qader et al, 2003), mathematical morphology (Sinha, Fieguth, 2006), high-speed percolation (Yamaguchi, Hashimoto, 2010), Principal Component Analysis (PCA) (Abdel-Qader et al, 2006), Extreme Learning Machine (Zhang et al, 2014) and Support Vector Machine (SVM) (Nashat et al, 2014) have been adopted. Furthermore, to improve the performances of image-based techniques and develop a method able to cover unexpected real-world situations, deep learning approaches (CNN -Convolutional Neural Network) have been also recently investigated (Li et al, 2018, Cha et al, 2017, Gopalakrishnan et al, 2017, Zou et al, 2018, Liu et al, 2019, Ren et al, 2020. Indeed, CNNs represent very powerful techniques for automatic feature extraction and classification problem and they have received considerable attention in the field of infrastructure monitoring thanks also to the spread of drones and other mobile mapping systems which can acquire a large amount of data.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, these techniques can easily handle a large amount of collected data. In the last years, three different deep learning approaches have been adopted to perform crack detection: object detection (Li et al, 2018), image classification (Cha et al, 2017) and semantic segmentation (Ren et al, 2020). The first one aims only at detecting the location of the cracks using bounding boxes without providing additional information such as the width and the shape of the cracks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Tack Project: Tunnel and Bridge Automatic Crack Monitoring Using Deep Learning and Photogrammetry

Belloni

Sjölander²,

Ravanelli

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Civil infrastructures, such as tunnels and bridges, are directly related to the overall economic and demographic growth of countries. The aging of these infrastructures increases the probability of catastrophic failures that results in loss of lives and high repair costs; all over the world, these factors drive the need for advanced infrastructure monitoring systems. For these reasons, in the last years, different types of devices and innovative infrastructure monitoring techniques have been investigated to automate the process and overcome the main limitation of standard visual inspections that are used nowadays. This paper presents some preliminary findings of an ongoing research project, named TACK, that combines advanced deep learning techniques and innovative photogrammetric algorithms to develop a monitoring system. Specifically, the project focuses on the development of an automatic procedure for crack detection and measurement using images of tunnels and bridges acquired with a mobile mapping system. In this paper, some preliminary results are shown to investigate the potential of a deep learning algorithm in detecting cracks occurred in concrete material. The model is a CNN (Convolutional Neural Network) based on the U-Net architecture; in this study, we tested the transferability of the model that has been trained on a small available labeled dataset and tested on a large set of images acquired using a customized mobile mapping system. The results have shown that it is possible to effectively detect cracks in unseen imagery and that the primary source of errors is the false positive detection of crack-like objects (i.e., contact wires, cables and tile borders).

show abstract

Section: Preliminary Results On Crack Segmentationmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tack Project: Tunnel and Bridge Automatic Crack Monitoring Using Deep Learning and Photogrammetry

Belloni

Sjölander²,

Ravanelli

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Then the damage evolution process is analyzed. At present, the analysis methods for concrete surface damage images include edge detection analysis, 19,[41][42][43] fractal analysis, [44][45][46] artificial neural network, [47][48][49][50][51] deep convolutional neural network, 19,[52][53][54][55] graylevel co-occurrence matrix (GLCM) 49,[55][56][57] , etc.…”

Section: Introductionmentioning

confidence: 99%

Analysis of steel corrosion‐induced surface damage evolution of magnesium oxychloride cement concrete through gray‐level co‐occurrence matrices

Wang

Huang

et al. 2020

Structural Concrete

View full text Add to dashboard Cite

In order to get the characteristics of crack formation on a concrete surface, a coupled method of industrial cameras and gray-level co-occurrence matrices (GLCM) is used to analyze the formation of magnesium oxychloride cement concrete surface cracks. This method requires fewer samples than the previous edge detection method, typing analysis, and artificial neural network method and can provide more damage parameter information without being limited to the geometric information of local features. According to the GLCM analysis of the surface crack formation of concrete under the effect of a rust expansion force, it is concluded that the larger the concrete protective layer, the longer the energization time required. When the concrete surface crack reaches 0.2 mm, the test pieces with protective layers of 14, 24, 34, and 44 mm need to be energized for 270, 465, 673, and 792 hr, respectively. With the increase of cracks on the concrete surface, the contrast keeps increasing, while the correlation, energy, and homogeneity gradually decrease. In color heat maps, the number of matrix peaks gradually increases with the formation of cracks, and the bandwidth of the horizontal projection of matrix peaks gradually decreases, and there is a tendency to extend along the main diagonal of the matrix. The selection of the size of the region of interest region will have a certain impact on the size of the four eigenvalues in GLCM, but it will not change its development law.

show abstract

Crack segmentation in the wild using convolutional neural networks and bootstrapping

Ahmad,

Gharehbaghi,

et al. 2023

Earthquake Engineering and Resilience

View full text Add to dashboard Cite

Computer vision and deep learning methods have found numerous practical applications over the last decade. The field of structural health monitoring has greatly benefited from such advancements. Accurate crack detection and segmentation are a critical part of structural health monitoring and assessment. In the past decade, researchers have developed different computer vision and deep learning methods to address this challenging task. In this article, we propose to use convolutional neural networks and bootstrapping to improve crack segmentation in the wild. Specifically, we investigate fully convolutional network (FCN) and DeepLabV3 with different ResNet architectures as the back bone and assess their performance. A unique feature of this work is the use of bootstrapping with a segmentation network and image augmentation. Bootstrapping is an important component of our proposed methodology for better extracting features from the datasets. We also incorporate superpixel pooling for FCN which improves performance. We assess the performance of our method using five publicly available datasets, which include a wide variety of crack images such as thin pavement cracks, tree shadows on cracks, cracks in asphalt roads, concrete wall cracks, wide cracks on concrete surfaces, and so on. A comparative study is also performed with several established methods in the literature. Results indicate that overall, our proposed method outperforms other state‐of‐the‐art methods for crack segmentation.

show abstract

Image-based concrete crack detection in tunnels using deep fully convolutional networks

Cited by 321 publications

References 29 publications

Tack Project: Tunnel and Bridge Automatic Crack Monitoring Using Deep Learning and Photogrammetry

Tack Project: Tunnel and Bridge Automatic Crack Monitoring Using Deep Learning and Photogrammetry

Analysis of steel corrosion‐induced surface damage evolution of magnesium oxychloride cement concrete through gray‐level co‐occurrence matrices

Crack segmentation in the wild using convolutional neural networks and bootstrapping

Contact Info

Product

Resources

About