TY - JOUR
T1 - CrackCLF
T2 - Automatic Pavement Crack Detection Based on Closed-Loop Feedback
AU - Li, Chong
AU - Fan, Zhun
AU - Chen, Ying
AU - Lin, Huibiao
AU - Moretti, Laura
AU - Loprencipe, Giuseppe
AU - Sheng, Weihua
AU - Wang, Kelvin C.P.
N1 - Publisher Copyright:
© 2000-2011 IEEE.
PY - 2024/6/1
Y1 - 2024/6/1
N2 - Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.
AB - Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.
KW - Automatic pavement crack detection
KW - closed-loop feedback
KW - deep learning
KW - encoder-decoder
KW - generative adversarial network
UR - http://www.scopus.com/inward/record.url?scp=85178027281&partnerID=8YFLogxK
U2 - 10.1109/TITS.2023.3332995
DO - 10.1109/TITS.2023.3332995
M3 - Article
AN - SCOPUS:85178027281
SN - 1524-9050
VL - 25
SP - 5965
EP - 5980
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
IS - 6
ER -