Road damage detection using super-resolution and semi-supervised learning with generative adversarial network

Shim, Seungbo; Kim, Jin; Lee, Seong-Won; Cho, Gye-Chun

doi:10.1016/j.autcon.2022.104139

Cited by 70 publications

(26 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mIoU is commonly used in the evaluation of image detection. 27,40 the mIoU represents the overlapping average accuracy. The calculation formula is shown in Equation (10).…”

Section: Evaluation Indicatorsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic segmentation of airport pavement damage by AM‐Mask R‐CNN algorithm

Zhang

Dong

Gao

2023

Engineering Reports

View full text Add to dashboard Cite

The airport is an important infrastructure for air transport and urban traffic. The airport pavement damage seriously affects the safety of aircraft take‐off and landing. Therefore, the regular detection of airport pavement damage is critical for aircraft take‐off and landing safety. However, for small target areas, the existing pavement damage detection methods cannot effectively achieve detection. In addition, the airport pavement detection is carried out under low light conditions at night, and the existing detection methods may not be able to accurately detect the damage boundary. To address the above problems, an automatic detection algorithm of Mask R‐CNN algorithm integrating attention mechanism (AM‐Mask R‐CNN) for airport pavement damage is proposed. First, the AM‐Mask R‐CNN is developed based on an improved Mask R‐CNN modified by the feature pyramid (FPN) and the dual attention mechanism are fused to extract subtle features in images. In addition, feature fusion is used. The macroscopic and microscopic features of airport pavement damage are organically combined to improve the segmentation sensitivity of small target areas and dark lighting. The experimental results show that the average F1‐score of the proposed model is 0.9489. In addition, the mean intersection over union for the model proposed is 0.9388. The average segmentation speed can reach 11.8 FPS. Moreover, compared with the traditional threshold segmentation method Fully Convolutional Networks (FCN) and DeepCrack segmentation method, the effectiveness of the proposed method is further proved.

show abstract

“…The mIoU is commonly used in the evaluation of image detection. 27,40 the mIoU represents the overlapping average accuracy. The calculation formula is shown in Equation (10).…”

Section: Evaluation Indicatorsmentioning

confidence: 99%

“…

\mathrm{F}1-\mathrm{score}=2\times \frac{P\times R}{P+R}.

The mIoU is commonly used in the evaluation of image detection 27,40 . the mIoU represents the overlapping average accuracy.…”

Section: Experimental Environment and Evaluation Indicatorsmentioning

confidence: 99%

Automatic segmentation of airport pavement damage by AM‐Mask R‐CNN algorithm

Zhang

Dong

Gao

2023

Engineering Reports

View full text Add to dashboard Cite

show abstract

“…For 400 road images, the average recognition rate reached 81.540% and 79.228%, respectively. Literature [110], [111], [112], [113], [114] has also made improvements and upgrades for GAN used in construction defect detection. Table 5 shows the research application and performance of GAN-based defect detection in the field of construction road quality inspection.…”

Section: Overview Of Gan-based Construction Road Defect Detection App...mentioning

confidence: 99%

A Survey of Defect Detection Applications Based on Generative Adversarial Networks

Chang²,

Zhang³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

“…SSL model is built with a small number of labeled samples and a large number of unlabeled samples. In practice, collecting labeled samples is often difficult, expensive, and time-consuming in practical conditions, while unlabeled samples are easy to obtain 2,3 . SSL will require as few people as possible to work and can also bring relatively high accuracy.…”

Section: Introductionmentioning

confidence: 99%

Haze pollution monitoring system based on semi-supervised learning

Liu

Wang

2023

International Conference on Computer Application and Information Security (ICCAIS 2022)

View full text Add to dashboard Cite

In this paper, a design of air pollutant monitoring system with six modules based on Semi-supervised learning (SSL) is designed. More specifically, the data acquisition module, data pre-processing module, data classifier module, comprehensive analysis module, auxiliary sorting module, computer terminal module respectively realize data collection, dimension reduction pre-processing, classification, comprehensive analysis, sorting, observation and monitoring. After system operation, it perfectly realized the real-time monitoring and timely warning of haze pollution, and provided data support for the precision of urban air pollution prevention. The application of modern science and technology in air pollution monitoring has been realized, and the ability and level of air pollution prevention and control supervision have been improved. The experimental results show that the proposed system has higher accuracy monitoring of classification．

show abstract

Road damage detection using super-resolution and semi-supervised learning with generative adversarial network

Cited by 70 publications

References 30 publications

Automatic segmentation of airport pavement damage by AM‐Mask R‐CNN algorithm

Automatic segmentation of airport pavement damage by AM‐Mask R‐CNN algorithm

A Survey of Defect Detection Applications Based on Generative Adversarial Networks

Haze pollution monitoring system based on semi-supervised learning

Contact Info

Product

Resources

About