Abstract
Highway agencies and practitioners expect to have the most efficient method with adequate accuracy when choosing a deep learning-based model for pavement crack classification. However, many works are implemented on their own dataset, making them hard to compare with each other, and also less persuasive and robust. Therefore, a Road Cracks Classification Dataset is proposed to serve as a standard and open-source dataset. Based on this dataset, a benchmark study of fourteen deep learning classification methods is evaluated. Two parameters, the Ratio of F1 and Training Time (RFT) and Ratio of F1 and Prediction Time (RFP), are proposed to quantify the efficiency of networks. The results show that ConvNeXt_base reaches the highest accuracy among all models but requires the longest training time. AlexNet takes the least training time among all models, but gains the lowest accuracy. Of the four crack types, the block crack has the lowest accuracy, which means it is the most difficult to detect. SqueezeNet1_0 has the highest efficiency among all models in converting the computing power to accuracy. Wide ResNet 50_2 consumes the longest prediction time among CNN models, while the ConvNeXt_base has the highest feasibility on real-time tasks. To implement a suitable deep learning-based pavement crack inspection, we recommend a good balance between computational cost and accuracy. Based on this, we provide practical recommendations according to different user groups.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Chen C, Chandra S, Han Y, Seo H (2021) Deep learning-based thermal image analysis for pavement defect detection and classification considering complex pavement conditions. Remote Sensing 14:106, DOI: https://doi.org/10.3390/rs14010106
Cui B, Wang H, Gu X, Hu D (2022) Study of the inter-diffusion characteristics and cracking resistance of virgin-aged asphalt binders using molecular dynamics simulation. Construction and Building Materials 351:128968, DOI: https://doi.org/10.1016/j.conbuildmat.2022.128968
Deng H, Gu X, Wang X, Ww C, Zhu, C (2019) Evaluation of high-temperature deformation of porous asphalt mixtures based on microstructure using X-ray computed tomography. Construction and Building Materials 227:116623, DOI: https://doi.org/10.1016/j.conbuildmat.2019.08.004
Deng J, Dong W, Socher R, Li LJ, Li K, Feifei L (2009) Imagenet: A large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition, Ieee, 248–255
Fei Y, Wang KC, Zhang A, Chen C, Li JQ, Liu Y, Yang G, Li B (2019) Pixel-level cracking detection on 3D asphalt pavement images through deep-learning-based CrackNet-V. IEEE Transactions on Intelligent Transportation Systems 21:273–284, DOI: https://doi.org/10.1109/TITS.2019.2891167
Gopalakrishnan K, Khaitan SK, Choudhary A, Agrawal A (2017) Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection. Construction and Building Materials 157:322–330, DOI: https://doi.org/10.1016/j.conbuildmat.2017.09.110
Han H, Deng H, Dong Q, Gu X, Zhang T, Wang Y (2021) An advanced Otsu method integrated with edge detection and decision tree for crack detection in highway transportation infrastructure. Advances in Materials Science and Engineering, 2021, DOI: https://doi.org/10.1155/2021/9205509
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778
Hou Y, Li Q, Han Q, Peng B, Wang L, Gu X, Wang D (2021) MobileCrack: Object classification in asphalt pavements using an adaptive lightweight deep learning. Journal of Transportation Engineering, Part B: Pavements 147:04020092, DOI: https://doi.org/10.1061/JPEODX.0000245
Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V (2019) Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision, 1314–1324
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700–4708
Huyan J, Li W, Tighe S, Xu Z, Zhai J (2020) CrackU-net: A novel deep convolutional neural network for pixelwise pavement crack detection. Structural Control and Health Monitoring 27:e2551, DOI: https://doi.org/10.1002/stc.2551
Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360
Kaddah W, Elbouz M, Ouerhani Y, Baltazart V, Desthieux M, Alfalou A (2019) Optimized minimal path selection (OMPS) method for automatic and unsupervised crack segmentation within two-dimensional pavement images. The Visual Computer 35:1293–1309, DOI: https://doi.org/10.1007/s00371-018-1515-9
Krizhevsky A (2014) One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997
Liu F, Liu J, Wang L (2022a) Deep learning and infrared thermography for asphalt pavement crack severity classification. Automation in Construction 140:104383, DOI: https://doi.org/10.1016/j.autcon.2022.104383
Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S (2022b) A convnet for the 2020s. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11976–11986
Liu J, Yang X, Lau S, Wang X, Luo S, Lee VCS, Ding L (2020) Automated pavement crack detection and segmentation based on two-step convolutional neural network. Computer-Aided Civil and Infrastructure Engineering 35:1291–1305, DOI: https://doi.org/10.1111/mice.12622
Liu Y, Yao J, Lu X, Xie R, Li L (2019) DeepCrack: A deep hierarchical feature learning architecture for crack segmentation. Neurocomputing 338:139–153, DOI: https://doi.org/10.1016/j.neucom.2019.01.036
Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the European Conference on Computer Vision (ECCV), 116–131.
Qu Z, Mei J, Liu L, Zhou DY (2020) Crack detection of concrete pavement with cross-entropy loss function and improved VGG16 network model. Ieee Access 8:54564–54573, DOI: https://doi.org/10.1109/ACCESS.2020.2981561
Que Y, Dai Y, Ji X, Leung AK, Chen Z, Tang Y, Jiang Z (2023) Automatic classification of asphalt pavement cracks using a novel integrated generative adversarial networks and improved VGG model. Engineering Structures 277:115406, DOI: https://doi.org/10.1016/j.engstruct.2022.115406
Radosavovic I, Kosaraju RP, Girshick R, He K, Dollar P (2020) Designing network design spaces. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10428–10436
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9
Tan M, Chen B, Pang R, Vasudevan V, Sandler M, Howard A, Le QV (2019) Mnasnet: Platform-aware neural architecture search for mobile. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2820–2828
Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. International Conference on Machine Learning, PMLR:6105–6114
Wang W, Su C (2021) Deep learning-based real-time crack segmentation for pavement images. KSCE Journal of Civil Engineering 25:4495–4506, DOI: https://doi.org/10.1007/s12205-021-0474-2
Wen T, Lang H, Ding S, Lu JJ, Xing Y (2022) PCDNet: Seed operation–based deep learning model for pavement crack detection on 3d asphalt surface. Journal of Transportation Engineering, Part B: Pavements 148:04022023, DOI: https://doi.org/10.1061/JPEODX.0000367
Xie S, Girshick R, Dollar P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1492–1500
Xu B, Liu C (2022) Pavement crack detection algorithm based on generative adversarial network and convolutional neural network under small samples. Measurement 196:111219, DOI: https://doi.org/10.1016/j.measurement.2022.111219
Yang F, Zhang L, Yu S, Prokhorov D, Mei X, Ling H (2019) Feature pyramid and hierarchical boosting network for pavement crack detection. IEEE Transactions on Intelligent Transportation Systems 21:1525–1535, DOI: https://doi.org/10.1109/TITS.2019.2910595
Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv preprint arXiv:1605.07146
Zhang T, Rahman MA, Peterson A, Lu Y (2022) Novel damage index-based rapid evaluation of civil infrastructure subsurface defects using thermography analytics. Infrastructures 7:55, DOI: https://doi.org/10.3390/infrastructures7040055
Zhang T, Wang D, Lu Y (2023a) ECSNet: An accelerated real-time image segmentation CNN architecture for pavement crack detection. IEEE Transactions on Intelligent Transportation Systems, DOI: https://doi.org/10.1109/TITS.2023.3300312
Zhang T, Wang D, Lu Y (2023b) Machine learning-enabled regional multi-hazards risk assessment considering social vulnerability. Scientific Reports 13:13405, DOI: https://doi.org/10.1038/s41598-023-40159-9
Zhang T, Wang D, Muffins A, Lu Y (2023c) Integrated APC-GAN and AttuNet framework for automated pavement crack pixel-level segmentation: A new solution to small training datasets. IEEE Transactions on Intelligent Transportation Systems, DOI: https://doi.org/10.1109/TITS.2023.3236247
Acknowledgments
We would like to appreciate the Federal Highway Administration (FHWA) for providing the pavement images (https://github.com/UM-Titan/DSPS).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, T., Wang, D. & Lu, Y. Benchmark Study on a Novel Online Dataset for Standard Evaluation of Deep Learning-based Pavement Cracks Classification Models. KSCE J Civ Eng 28, 1267–1279 (2024). https://doi.org/10.1007/s12205-024-1066-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-024-1066-8