Road Crack Image Segmentation Using Global Context U-net

Chen, Jie; Liu, Gang; Chen, Xin

doi:10.1145/3374587.3374602

Cited by 9 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cao et al [ 8 ] replaced the U-Net encoder with ResNet34 to deal with the loss of spatial information caused by continuous pooling. Effectively avoiding gradient disappearance or gradient explosion, Chen et al [ 9 ] embedded a global context module in the U-Net network structure to give the network the ability to capture global context information, which is conducive to the detailed segmentation of pavement crack images. Augustauskas and Lipnickas [ 10 ] introduced a kind of attention based on the U-shaped network.…”

Section: Introductionmentioning

confidence: 99%

A Pavement Crack Detection Method Based on Multiscale Attention and HFS

Shi

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To solve the problem of low detection accuracy due to the loss of detailed information when extracting pavement crack features in traditional U-shaped networks, a pavement crack detection method based on multiscale attention and hesitant fuzzy set (HFS) is proposed. First, the encoding-decoding structure is used to construct a pavement crack segmentation network, ResNeXt50 is used to extract features in the encoding stage, and a multiscale feature fusion module (MFF) is designed to obtain multiscale context information. Second, in the decoding stage, a high-efficiency dual attention module (EDA) is used to enhance the ability of capturing details of the cracks while suppressing background noise. Finally, the membership degree of the crack is calculated based on the advantages of the HFS in multiattribute decision-making to obtain the similarity of the crack, and the binary image after segmentation is judged by the hesitation fuzzy measure. The experiment was conducted on the public road crack dataset Crack500. In terms of segmentation performance, the evaluation indexes Intersection over Union (IoU), Precision, and Dice coefficients of the proposed network reached 55.56%, 74.26%, and 67.43%, respectively; in terms of classification performance, for transversal and longitudinal cracks, the classification accuracy was 84% ± 0.5%, while the block and the alligator were both 78% ± 0.5%. The experimental results prove that the crack details detected by the proposed method are more abundant, and the image detection effect of complex topological structures and small cracks are better.

show abstract

Section: Introductionmentioning

confidence: 99%

A Pavement Crack Detection Method Based on Multiscale Attention and HFS

Shi

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Zhang et al, 2019). Our implementation is based on the work presented in (Chen, Liu, & Chen, 2019) and has achieved normal performance on this segmentation task.…”

Section: Resultsmentioning

confidence: 99%

The Future of PHM Could be Tiny under Cloud: Exploring Potential Application Patterns of TinyML in PHM Scenarios

et al. 2021

View full text Add to dashboard Cite

Deep learning has shown impressive performance acrosshealth management and prognostics applications. Nowadays, an emerging trend of machine learning deployment on resource constraint hardware devices like micro-controllers(MCU) has aroused much attention. Given the distributed andresource constraint nature of many PHM applications, using tiny machine learning models close to data source sensors for on-device inferences would be beneficial to save both time andadditional hardware resources. Even though there has beenpast works that bring TinyML on MCUs for some PHM ap-plications, they are mainly targeting single data source usage without higher-level data incorporation with cloud computing.We study the impact of potential cooperation patterns betweenTinyML on edge and more powerful computation resources oncloud and how this would make an impact on the application patterns in data-driven prognostics. We introduce potential ap-plications where sensor readings are utilized for system health status prediction including status classification and remaining useful life regression. We find that MCUs and cloud com-puting can be adaptive to different kinds of machine learning models and combined in flexible ways for diverse requirement.Our work also shows limitations of current MCU-based deep learning in data-driven prognostics And we hope our work can

show abstract

“…U‐Net produces the best F1 score over non‐deep learning methods on the CrackForest dataset; there seem to be no obvious thick results but also no illustrated results about how the model performed on images with significant shadow. In Global Context U‐Net (Chen et al., 2019), U‐Net is modified to include the lightweight global context blocks that utilize the attention mechanism to make the model focus on the global context information and long‐distance dependency information. This work uses the normal binary cross‐entropy loss, and the results on the Crack500 dataset are better than the original U‐Net.…”

Section: Related Workmentioning

confidence: 99%

Pixel‐level thin crack detection on road surface using convolutional neural network for severely imbalanced data

Siriborvornratanakul

2023

Computer aided Civil Eng

View full text Add to dashboard Cite

Because roads are the major backbone of the transportation network, research about crack detection on road surfaces has been popular in computer and infrastructure engineering. When training a convolutional neural network (CNN) for pixel‐level road crack detection, three common challenges include (1) the data are severely imbalanced, (2) crack pixels can be easily confused with normal road texture and other visual noises, and (3) there are many unexplainable characteristics regarding the CNN itself. When it comes to very fine and thin cracks, these challenges are exaggerated and a new challenge is introduced, as there can be a discrepancy between the actual width and the annotated width of a crack. To tackle all these challenges of thin crack detection, this paper proposes a new variant of CNN named ThinCrack U‐Net, designed to provide thin results upon pixel‐level crack detection on road surfaces. The main contribution is to demystify how pixel‐level thin crack detection results are affected by different loss functions as well as various combinations of the U‐Net components. The experimental results show that ThinCrack U‐Net yields a significant performance boost in CrackTree260, from 65.71% to 94.48% F‐measure, compared to the existing variant of U‐Net previously proposed in the context of pixel‐level thin crack detection. Finally, this paper locates the source of undesirable result thickness and solves it with the balanced usage of downsampling/upsampling layers and atrous convolution. Unlike suggested by previous works, different loss functions show no significant impact on ThinCrack U‐Net, whereas normalization layers are proved crucial in pixel‐level thin crack detection.

show abstract

Road Crack Image Segmentation Using Global Context U-net

Cited by 9 publications

References 11 publications

A Pavement Crack Detection Method Based on Multiscale Attention and HFS

A Pavement Crack Detection Method Based on Multiscale Attention and HFS

The Future of PHM Could be Tiny under Cloud: Exploring Potential Application Patterns of TinyML in PHM Scenarios

Pixel‐level thin crack detection on road surface using convolutional neural network for severely imbalanced data

Contact Info

Product

Resources

About