Pavement Image Data Set for Deep Learning: A Synthetic Approach
Publication: Airfield and Highway Pavements 2021
ABSTRACT
Deep learning methods have shown a promising approach to reliable automated pavement condition survey in recent years. However, the training of models requires large quantities of annotated data, which is normally time consuming, expensive, and sometimes difficult to obtain. This research aims to explore the viability of using synthetic pavement image data to train convolutional neural networks (CNNs) for automated pavement crack detection. A procedural approach of generating synthetic pavement crack image data is proposed. Perlin noise is adopted to mimic the real-world cracks, and simple textures are used to control the generated crack type. Mask R-CNN is used to train on the synthetic data developed in this study. Both synthetic and real data sets are used to evaluate the performance of the trained model. The results indicate that training a crack detection model using only synthetic data can reach almost the same level of accuracy as using the real data.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Ayenu-Prah, A., and Attoh-Okine, N. (2008). “Evaluating pavement cracks with bidimensional empirical mode decomposition.” EURASIP J. Adv. Signal Process, article number: 861701.
FHWA (Federal Highway Administration). (2014). Distress identification manual for the long-term pavement performance program, United States.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). “Rich feature hierarchies for accurate object detection and semantic segmentation.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 580-587.
Gustavson, S. (2005). “Simplex noise demystified.” Linköping University, Linköping, Sweden,.
Handa, A., Patraucean, V., Badrinarayanan, V., Stent, S., and Cipolla, R. (2016). “Understanding real world indoor scenes with synthetic data.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 4077-4085.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). “Deep residual learning for image recognition.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 770-778.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). “Mask r-cnn.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 2961-2969.
Iben, H. N., and O’brien, J. F. (2009). “Generating surface crack patterns.” Graphical Models, 71(6), 198-208.
Jetchev, N., Bergmann, U., and Vollgraf, R. (2016). “Texture synthesis with spatial generative adversarial networks.”.
Kargah-Ostadi, N., Nazef, A., Daleiden, J., and Zhou, Y. (2017). “Evaluation Framework for Automated Pavement Distress Identification and Quantification Applications.” Transp. Res. Rec., 2639(1), 46-54.
Majidifard, H., Jin, P., Adu-Gyamfi, Y., and Buttlar, W.G. (2020). “Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses.” Transp. Res. Rec., 2674(2), 328-339.
Mandal, V., Uong, L., and Adu-Gyamfi, Y. (2018). “Automated road crack detection using deep convolutional neural networks.” In 2018 IEEE Int. Conf. Big Data: IEEE, 5212-5215.
Martinet, A., Galin, E., Desbenoit, B., and Akkouche, S. (2004). “Procedural modeling of cracks and fractures.” In Proc. Shape Modeling Appl.: IEEE, 346-349.
Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., and Brox, T. (2016). “A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 4040-4048.
Oliveira, H., and Correia, P.L. (2009). “Automatic road crack segmentation using entropy and image dynamic thresholding.” In 17th European Signal Processing Conf.: IEEE, 622-626.
Perlin, K. (1985). “An image synthesizer.” ACM Siggraph Comput. Graphics, 19(3), 287-296.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). “You only look once: Unified, real-time object detection.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 779-788.
Santhi, B., Krishnamurthy, G., Siddharth, S., and Ramakrishnan, P.K. (2012). “Automatic detection of cracks in pavements using edge detection operator.” J. Theor. Appl. Inf. Technol., 36(2), 199-205.
Shi, Y., Cui, L., Qi, Z., Meng, F., and Chen, Z. (2016). “Automatic road crack detection using random structured forests.” IEEE Trans. Intell. Transp. Syst., 17(12), 3434-3445.
Stricker, R., Eisenbach, M., Sesselmann, M., Debes, K., and Gross, H. M. (2019). “Improving visual road condition assessment by extensive experiments on the extended gaps dataset.” In 2019 Int. Joint Conf. Neural Networks (IJCNN): IEEE, 1-8.
Subirats, P., Dumoulin, J., Legeay, V., and Barba, D. (2006). “Automation of pavement surface crack detection using the continuous wavelet transform.” In 2006 Int. Conf. Image Processing: IEEE, 3037-3040.
Tremblay, J., Prakash, A., Acuna, D., Brophy, M., Jampani, V., Anil, C., To, T., Cameracci, E., Boochoon, S., and Birchfield, S. (2018). “Training deep networks with synthetic data: Bridging the reality gap by domain randomization.” In Proc. IEEE Conf. on Comput. Vision and Pattern Recognit.: IEEE, 969-977.
TxDOT (Texas Department of Transportation). (2019). Pavement Manual, TxDOT, TX.
Wang, K. C., Li, Q., and Gong, W. (2007). “Wavelet-based pavement distress image edge detection with A Trous algorithm.” Transp. Res. Rec., 2024(1), 73-81.
Yang, F., Zhang, L., Yu, S., Prokhorov, D., Mei, X., and Ling, H. (2019). “Feature pyramid and hierarchical boosting network for pavement crack detection.” IEEE Trans. Intell. Transp. Syst., 21(4), 1525-1535.
Ying, L., and Salari, E. (2010). “Beamlet transform-based technique for pavement crack detection and classification.” Computer-Aided Civ. and Infrastruct. Eng., 25(8), 572-580.
Zhang, A., Wang, K. C., Li, B., Yang, E., Dai, X., Peng, Y., Fei, Y., Liu, Y., Li, J. Q., and Chen, C. (2017). “Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network.” Computer-Aided Civ. and Infrastruct. Eng., 32(10), 805-819.
Zhang, A., Wang, K. C., Fei, Y., Liu, Y., Chen, C., Yang, G., Li, J. Q., Yang, E., and Qiu, S. (2019). “Automated pixel-level pavement crack detection on 3D asphalt surfaces with a recurrent neural network.” Computer-Aided Civ. and Infrastruct. Eng., 34(3), 213-229.
Zhang, D., Li, Q., Chen, Y., Cao, M., He, L., and Zhang, B. (2017). “An efficient and reliable coarse-to-fine approach for asphalt pavement crack detection.” Image Vision Comput., 57, 130-146.
Zhang, L., Yang, F., Zhang, Y. D., and Zhu, Y. J. (2016). “Road crack detection using deep convolutional neural network.” In 2016 Int. Conf. Image Processing: IEEE, 3708-3712.
Information & Authors
Information
Published In
Airfield and Highway Pavements 2021
Pages: 253 - 263
Copyright
© 2021 American Society of Civil Engineers.
History
Published online: Jun 4, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.