CrackGAN: Pavement Crack Detection Using Partially Accurate Ground Truths Based on Generative Adversarial Learning

Zhang, Kaige; Zhang, Yingtao; Cheng, Heng-Da

doi:10.1109/tits.2020.2990703

Cited by 127 publications

(61 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first dataset consists of a set of photographs from the Unsupervised Llamas dataset [21] and the same images without any additional items other than the roadway (henceforth referred to as the "Dashboard image dataset"). We manually removed superfluous items from the dataset images in order to create a dataset of examples for training our network that excluded unneeded objects.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…To evaluate the effectiveness of the proposed technique, various competitive methods were selected, such as CrackIT [15], CrackForest [10], FCN-VGG [14], DeepCrack-1 [16], DeepCrack-2 [16], Pix2pix GAN [25], and CrackGAN [21]. For accurate comparison with our results, we ran experiments using the same equipment and platform environment, as well as both the Dashboard image dataset and the Roadway fractures dataset.…”

Section: Evaluation Metricmentioning

confidence: 99%

“…All of these characteristics greatly reduce the efficacy of methods given in the related research. For example, CrackGAN [21] finds cracks throughout the image, despite the fact that detection of cracks on side-walks or the roadway edge consumes additional power capacity for ineffective difficulties. As a result, the selection measurement rate of CrackGAN is low.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Kyslytsyna

Xia

Kislitsyn³

et al. 2021

Sensors

View full text Add to dashboard Cite

Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detection. The advantage of this method is the highly accurate results in vector-based images, which are convenient for mathematical analysis of the detected cracks at a later time. However, images taken under established parameters are different from images in real-world contexts. Another potential problem of cGAN is that it is difficult to detect the shape of an object when the resulting accuracy is low, which can seriously affect any further mathematical analysis of the detected crack. To tackle this issue, this paper proposes a method called improved cGAN with attention gate (ICGA) for roadway surface crack detection. To obtain a more accurate shape of the detected target object, ICGA establishes a multi-level model with independent stages. In the first stage, everything except the road is treated as noise and removed from the image. These images are stored in a new dataset. In the second stage, ICGA determines the cracks. Therefore, ICGA focuses on the redistribution of cracks, not the auxiliary elements in the image. ICGA adds two attention gates to a U-net architecture and improves the segmentation capacities of the generator in pix2pix. Extensive experimental results on dashboard camera images of the Unsupervised Llamas dataset show that our method has better performance than other state-of-the-art methods.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Evaluation Metricmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Kyslytsyna

Xia

Kislitsyn³

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…FCN [4] [5], U-Net [6] [7], DeepCrack [8], I-UNet [9], etc. Other methods such as Mask R-CNN [10] and GAN [11] can also be used for pixel-level crack detection. The method based on object detection is to use bounding boxes to locate the crack area and determine the type of crack.…”

Section: A Related Workmentioning

confidence: 99%

Pavement Crack Detection Using Multi-stage Structural Feature Extraction Model

Duan

Zeng

Pang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Pavement crack detection is of great significance for road maintenance. However, the complexity of road surfaces and the irregularity of cracks make it difficult to accurately detect crack regions. We propose a crack detection method based on structural features for the patch-wise crack detection. The novelty of this method lies on the fusion of the local patches in a multistaged strategy. Deep supervision learning is further used to learn these features at each stage. The fusion features model the structural relevance among cracks. The experimental results prove the effectiveness of our method on the dataset collected from the industrial environments. Among these state-of-the-art methods we compared, our model achieved the best experimental results with an AP 86.97%.

show abstract

“…To address the aforementioned task, several methods designed for crack segmentation/detection have been proposed [4,5,6,7,8,9,10,11]. Zhou et al [4] propose Deep-Crack which learns multi-scale deep features to capture line Input Image Initial Pred.…”

Section: Introductionmentioning

confidence: 99%

Crack Detection and Refinement Via Deep Reinforcement Learning

Park

Chen

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Detecting small cracks in concrete is difficult due to the complexity and thinness of cracking patterns, which requires the development of refined vision-based segmentation algorithms that can accurately characterize the details of crack defects. While existing methods are good at generally outlining cracks, due to inherent differences in shape distributions between common objects and cracks, their predictions often have disconnected segments and inaccuracy along boundaries. To this end, we develop a refinement framework using reinforcement learning (RL) that can better recognize details specific to cracks. Our method uses an RL agent to iteratively improve per-pixel crack predictions of a general segmentation model. We find that in addition to connecting gaps in predictions, the RL agent is also able to detect cracks that are missed in the original predictions. It does so by using the originally detected regions as crack priors to branch out from. Refining outputs of a commonly used per-pixel segmentation model, our method outperforms the current state-of-theart approaches for crack segmentation. Our experiments also demonstrate that our method generalizes well to a similar task of vessel segmentation.

show abstract

CrackGAN: Pavement Crack Detection Using Partially Accurate Ground Truths Based on Generative Adversarial Learning

Cited by 127 publications

References 44 publications

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Pavement Crack Detection Using Multi-stage Structural Feature Extraction Model

Crack Detection and Refinement Via Deep Reinforcement Learning

Contact Info

Product

Resources

About