A Deep Learning Based Road Distress Visual Inspection System Using Modified U-Net

Siriborvornratanakul, Thitirat

doi:10.1007/978-3-030-90966-6_25

Cited by 8 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper presented here is different from (Siriborvornratanakul, 2018) and (Siriborvornratanakul, 2021). Siriborvornratanakul (2018)…”

Section: Introductionmentioning

confidence: 86%

“…In addition, although many variants of U-Net have been proposed one after another, no work has thoroughly investigated and concluded about what are the key factors that increase or decrease the performance of U-Net in pixel-level crack detection, particularly in the context of pixel-level thin crack detection. Last but not least, the previous work of Modified U-Net (Siriborvornratanakul, 2021) trained with the normal binary cross-entropy loss, unexplainably shows thick crack detection results that no previous work in U-Net for crack detection has ever discussed. This is perhaps because Modified U-Net is trained in the context of pixel-level thin crack detection where ground truth images involve one-pixel-wide crack annotations, whereas other previous works of U-Net experiment with the long-time popular crack dataset like CrackForest with arbitrary-width crack annotations.…”

Section: Related Workmentioning

confidence: 97%

“…The architecture of Modified U-Net (Siriborvornratanakul, 2021). Note that the drawing style of this figure is mostly inspired by the U-Net's figure in Ronneberger et al (2015).…”

Section: Alternative Loss Functions For Severely Imbalanced Datamentioning

confidence: 99%

“…Under the context of pixel‐level thin crack detection, previous works like DeepCrack (Zou et al., 2019) and Modified U‐Net (Siriborvornratanakul, 2021) tackle the challenges differently. DeepCrack constructs a whole new CNN architecture and yields good results on pixel‐level thin crack detection.…”

Section: Introductionmentioning

confidence: 99%

“…is about vision-based pothole detection using handcrafted features, whereas this paper is about vision-based crack detection using deep learning Siriborvornratanakul (2021). is about deep learning-based crack detection that falls in the same problem category as this paper.…”

mentioning

confidence: 99%

See 4 more Smart Citations

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

Siriborvornratanakul

2023

Computer aided Civil Eng

Self Cite

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

“…The paper presented here is different from (Siriborvornratanakul, 2018) and (Siriborvornratanakul, 2021). Siriborvornratanakul (2018)…”

Section: Introductionmentioning

confidence: 86%

Section: Related Workmentioning

confidence: 97%

“…The architecture of Modified U-Net (Siriborvornratanakul, 2021). Note that the drawing style of this figure is mostly inspired by the U-Net's figure in Ronneberger et al (2015).…”

Section: Alternative Loss Functions For Severely Imbalanced Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

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

Siriborvornratanakul

2023

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

Identification of Strategic Planning Factors to Achieve Smart Mobility for New Cities in Developing Countries Using CIB Method

Fadel,

Abu-Eisheh

2024

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)

View full text Add to dashboard Cite

A generative adversarial network approach for removing motion blur in the automatic detection of pavement cracks

Zhang,

Zhang

2024

Computer aided Civil Eng

View full text Add to dashboard Cite

Advancements in infrastructure management have significantly benefited from automatic pavement crack detection systems, relying on image processing enhanced by high‐resolution imaging and machine learning. However, image and motion blur substantially challenge the accuracy of crack detection and analysis. Nevertheless, research on mitigating motion blur remains sparse. This study introduces an effective image processing system adept at deblurring and segmentation, employing a generative adversarial network (GAN) with UNet as the generator and Wasserstein GAN with Gradient Penalty (WGAN‐gp) as the loss function. This approach performs exceptionally in deblurring pavement crack images and improves segmentation accuracy. Models were trained with sharp and artificially blurred images, with WGAN‐gp surpassing other loss functions in effectiveness. This research innovatively suggests assessing deblurring quality through segmentation accuracy in addition to peak signal‐to‐noise ratio (PSNR) and structural similarity (SSIM), revealing that PSNR and SSIM may not fully capture deblurring effectiveness for pavement crack images. An extensive evaluation of various generators, including UNet, lightweight UNet, TransUNet, DeblurGAN, DeblurGAN‐v2, and MIMO‐UNet, identifies the superior performance of UNet on simulated motion blur. Validation with actual motion‐blurred images confirms the effectiveness of the proposed model. These findings demonstrate that GAN‐based models have great potential in overcoming motion blur challenges in pavement crack detection systems, marking a notable advancement in the field.

show abstract

A Deep Learning Based Road Distress Visual Inspection System Using Modified U-Net

Cited by 8 publications

References 11 publications

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

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

Identification of Strategic Planning Factors to Achieve Smart Mobility for New Cities in Developing Countries Using CIB Method

A generative adversarial network approach for removing motion blur in the automatic detection of pavement cracks

Contact Info

Product

Resources

About