Real-Time Tunnel Crack Analysis System via Deep Learning

Song, Qing; Wu, Yingqi; Xin, Xueshi; Yang, Lu; Yang, Min; Chen, Hongming; Li, Chun; Hu, Mengjie; Chai, Xiaodong; Li, Jianchao

doi:10.1109/access.2019.2916330

Cited by 55 publications

(24 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the accuracy and efficiency of the object detection performance, a segmentation procedure has been developed to detect surface cracks of structures. This semantic crack segmentation approach is known as the pixel-wise CNN approach, and examples include the DeepLabv3-based network [50], the FCN-based network [51][52], the encoder-decoder network [53], DeepCrack [54], U-Net [55][56], FPCNet [57], and residual connections [58]. However, these approaches require a considerable amount of time to mark cracks at the pixel level.…”

Section: Deep Learning-based Approachmentioning

confidence: 99%

FCN-SFW: Steel Structure Crack Segmentation Using a Fully Convolutional Network and Structured Forests

et al. 2020

View full text Add to dashboard Cite

Tiny cracks that exist in steel beams have poor continuity and low contrast in images, posing a huge challenge to crack detection using image-based approaches. When complex backgrounds exist, the existing deep learning methods are usually unable to perform effective feature transfer and fusion for crack feature mapping, and they cannot accurately distinguish crack features from similar backgrounds. In this article, we propose a fusion segmentation algorithm, using the fully convolutional network (FCN) and structured forests with wavelet transform (SFW) to detect tiny cracks in steel beams. First, five neural networks based on the FCN framework are constructed to extend the global characteristics of tiny cracks. Second, a fine edge detection approach using multi-scale structured forests and wavelet maximum modulus edge detection to refine the characteristics of tiny cracks are proposed. Here, a competitive training strategy is used to address the SFW parameter optimization problem. Finally, we fuse the multiple probability maps, acquired from both the optimal FCN model and the SFW classifier, into a merged map, which can segment tiny cracks with robustness better than the comparison approaches. The experimental results show that compared with state-of-the-art algorithms and other segmentation approaches, the proposed algorithm realizes better segmentation in terms of quantitative metrics. INDEX TERMS Steel structure crack segmentation, fully convolutional network, structured forests, wavelet transform, maximum modulus edge detection.

show abstract

Section: Deep Learning-based Approachmentioning

confidence: 99%

FCN-SFW: Steel Structure Crack Segmentation Using a Fully Convolutional Network and Structured Forests

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In [2], a CNN-based crack detection algorithm and a fusion method using naive Bayesian algorithm are proposed to identify crack components in nuclear power plants. In [13] a deep learning-based segmentation algorithm is proposed to identify cracks in a tunnel. In [3,14,15,16,17] the CNN has been used for crack detection by the supervision of block-based classification.…”

Section: Related Workmentioning

confidence: 99%

“…However, many noises or other tiny pores and scratches on the surfaces make cracks difficult to be detected in the real world. The task is even more challenging when the surfaces of concretes are damaged by various factors [9,10,11,12,13,14]. For instance, Figure 1 shows parts of fire-damaged concretes.…”

Section: Introductionmentioning

confidence: 99%

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Lee

Kim

et al. 2019

Sensors

View full text Add to dashboard Cite

Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an autonomous crack detection algorithm based on convolutional neural network (CNN) to solve the problem. To this aim, the proposed algorithm uses a two-branched CNN architecture, consisting of sub-networks named a crack-component-aware (CCA) network and a crack-region-aware (CRA) network. The CCA network is to learn gradient component regarding cracks, and the CRA network is to learn a region-of-interest by distinguishing critical cracks and noise such as scratches. Specifically, the two sub-networks are built on convolution-deconvolution CNN architectures, but also they are comprised of different functional components to achieve their own goals efficiently. The two sub-networks are trained in an end-to-end to jointly optimize parameters and produce the final output of localizing important cracks. Various crack image samples and learning methods are used for efficiently training the proposed network. In the experimental results, the proposed algorithm provides better performance in the crack detection than the conventional algorithms.

show abstract

“…Gulsah et al [11] utilized a deep learning method for detecting arcs in pantograph-catenary systems. Qing et al [12] proposed an objective and fast tunnel crack identification algorithm based on the ResNet18 CNN to construct a complete tunnel crack identification and analysis system. Juan et al [13] designed an FB-NET detection model based on a deep learning method to detect railway shapes and dangerous obstacles.…”

Section: Related Workmentioning

confidence: 99%

Detection of Foreign Matter on High-Speed Train Underbody Based on Deep Learning

Yao

Jiang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

When a high-speed train is running, it is easy for foreign objects like rail-side plastic bags to enter bottom bogies, cables and equipment gaps, which affects the safety of driving. At present, the detection accuracy of such foreign objects is low. To solve this problem, the present study used the latest deep learning based object detection networks, such as SSD and Faster R-CNN, which combined with different feature extractors to build a detection network. Through data augmentation of a sample, the number of sizes was expanded. By the idea of transfer learning, the COCO dataset was used as the source data to transfer features to the new detection network and then retrained to build a train bottom plastic bag detection network based on deep learning. It was shown that through data augmentation, the precision of each combination significantly improved. Moreover, the results using combination of SSD and MobileNet obtained the fastest detection speed with an average time of 41 ms and a precision rate of 81.3%. The accuracy using combination of SSD + Inception V2 combination reached to 89.7%, with an average time of 53 ms. INDEX TERMS Deep learning, foreign matter on underbody, transfer learning, data augmentation, highspeed train.

show abstract

Real-Time Tunnel Crack Analysis System via Deep Learning

Cited by 55 publications

References 13 publications

FCN-SFW: Steel Structure Crack Segmentation Using a Fully Convolutional Network and Structured Forests

FCN-SFW: Steel Structure Crack Segmentation Using a Fully Convolutional Network and Structured Forests

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Detection of Foreign Matter on High-Speed Train Underbody Based on Deep Learning

Contact Info

Product

Resources

About