Deep-learning based non-contact method for assessing pavement skid resistance using 3D laser imaging technology

References

• Anupam, K., et al., 2013. Influence of temperature on tire-pavement friction analyses. Transportation Research Record, 2369, 114–124. https://doi.org/10.3141/2369-13.
   Web of Science ®Google Scholar
• Association for Safe International Road Travel, 2018. Road safety facts. http://web.archive.org/web/20181219165003/https://www.asirt.org/safe-travel/road-safety-facts/ (Accessed February 18, 2021).
   Google Scholar
• Aversano, L., et al., 2020. Tomato diseases classification based on VGG and transfer Learning. IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), 129–133, DOI: 10.1109/MetroAgriFor50201.2020.9277626.
   Google Scholar
• Cerezo, V., et al., 2014. Friction/water depth relationship-In site observations and its integration in tire/road friction models. Proceedings of the Institution of Mechanical Engineers Part J, 228 (11), 1285–1297. https://doi.org/10.1177/1350650114544533.
   Web of Science ®Google Scholar
• Chan, C, 2012. Monitoring and improving roadway surface conditions for safe driving environment and sustainable infrastructure. CA, 12–2199. California Department of Transportation, Sacramento, CA.
   Google Scholar
• Chollet, F, 2017. Deep learning with Python. Manning Publications Co., Shelter Island. NY.
   Google Scholar
• Deng, Q., et al., 2021. Multiscale power spectrum analysis of 3D surface texture for prediction of asphalt pavement friction. Construction and Building Materials, 293, 123506. https://doi.org/10.1016/j.conbuildmat.2021.123506.
   Web of Science ®Google Scholar
• Echaveguren, T., and Solminihac, H, 2011. Seasonal variability of skid resistance in paved roadways. Proceedings of the Institution of Civil Engineers – Transport, 164 (TRI1), 23–32. https://doi.org/10.1680/tran.9.00007.
   Google Scholar
• Echaveguren, T., Solminihac, H., and Chamorro, A, 2010. Long-term behaviour model of skid resistance for asphalt roadway surfaces. Canadian Journal of Civil Engineering, 37, 719–727. https://doi.org/10.1139/L10-021.
   Web of Science ®Google Scholar
• Federal Highway Administration (FHWA), 2010. Pavement Friction Management. Technical Advisory: T 5040.38.
   Google Scholar
• Federal Highway Administration (FHWA), 2021. Roadway departure safety. Washington, DC. https://safety.fhwa.dot.gov/roadway_dept/ (Accessed July 1, 2021).
   Google Scholar
• Fei, Y., et al., 2020. Pixel-level cracking detection on 3D asphalt pavement images through deep-learning-based CrackNet-V. IEEE Transactions on Intelligent Transportation Systems, 21 (1), 273–284.
   Web of Science ®Google Scholar
• Gardezi, S.J.S., et al., 2017. Mammogram classification using deep learning features. IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 485–488. DOI: 10.1109/ICSIPA.2017.8120660.
   Google Scholar
• Hall, J.W, et al., 2009. NCHRP web document 108: Guide for pavement friction. Washington, D.C: Transportation Research Board, National Research Council.
   Google Scholar
• He, K, et al., 2015a. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. arXiv:1502.01852.
   Google Scholar
• He, K, et al., 2015b. Deep residual learning for image recognition. arXiv:1512.03385.
   Google Scholar
• Huang, Y, 2012. New technologies for pavement evaluation. TxDOT 3-D pavement survey technology. The 86th Annual Transportation Short Course at Texas A&M University. https://static.tti.tamu.edu/conferences/tsc12/presentations/maint-pavement-mgmt/huang.pdf (Accessed June 11, 2021).
   Google Scholar
• Huang, H., et al., 2018. Railway infrastructure defects recognition using fine-grained deep convolutional neural networks. Digital Image Computing: Techniques and Applications (DICTA), 1–8. DOI: 10.1109/DICTA.2018.8615868.
   Google Scholar
• Izeppi, E.L., et al., 2017. Evaluation of methods for pavement surface friction, testing on non-tangent roadways and segments. FHWA/NC/, 2017–2002. Virginia Tech Transportation Institute, Blacksburg, VA.
   Google Scholar
• Kanafi, M.M., and Tuononen, A.J, 2017. Top topography surface roughness power spectrum for pavement friction evaluation. Tribology International, 107, 240–249.
   Web of Science ®Google Scholar
• Laurent, J., et al., 2016. High-speed network level road texture evaluation using 1 mm resolution transverse 3D profiling sensors using a digital sand patch model. https://www.pavemetrics.com/wp-content/uploads/2016/04/LCMS_Texture.pdf (Accessed May 15, 2021).
   Google Scholar
• Lee, H., Hall, J., and Stanley, M, 2019. Develop statistical models quantifying the relationship between pavement surface friction characteristics and traffic accident rates. FDOT BE385. Gainesville, FL: Florida Department of Transportation.
   Google Scholar
• Li, Q., et al., 2017. Novel macro- and microtexture indicators for pavement friction by using high-resolution three-dimensional surface data. Transportation Research Record, 2641, 164–176. https://doi.org/10.3141/2641-19.
   Google Scholar
• Li, Q., et al., 2021. Utilizing pavement friction and texture data for the reduction of traffic crashes and delays. FHWA-OK-21-01. Oklahoma Department of Transportation, Oklahoma City, OK.
   Google Scholar
• Li, L., Wang, K., and Li, Q, 2016. Geometric texture indicators for safety on AC pavements with 1-mm 3D laser texture data. International Journal of Pavement Research and Technology, 9, 49–62. https://doi.org/10.1016/j.ijprt.2016.01.004.
   Google Scholar
• Llopis-Castelló and Findley, 2019. Influence of calibration factors on crash prediction on rural two-lane two-wats roadway segments. Journal of Transportation Engineering. Part A: Systems, 04019024. DOI:10.1061/JTEPBS.0000245.
   Google Scholar
• Mandal, V., Mussah, A.R., and Adu-Gyamfi, Y., 2020. Deep learning frameworks for pavement distress classification: A comparative analysis. arXiv:2010.10681 [cs.CV].
   Google Scholar
• McGovern, C., Rusch, P., and Noyce, D.A, 2011. State practices to reduce wet weather skidding crashes. FHWA-SA-11-21. Washington, DC: Federal Highway Administration.
   Google Scholar
• Meegoda, J.N., 2009. Non-contact skid resistance measurement. FHWA-NJ-2009-020. New Jersey Department of Transportation, Trenton, NJ.
   Google Scholar
• National Academies of Sciences, Engineering, and Medicine (NASEM), 2018. Practices for preventing roadway departures. Washington, DC: The National Academies Press. https://doi.org/10.17226/25165
   Google Scholar
• National Academies of Sciences, Engineering, and Medicine (NASEM), 2020. Standard definitions for common types of pavement cracking. Washington, DC: The National Academies Press. https://doi.org/10.17226/25928
   Google Scholar
• Ng, A., et al., 2021. Unsupervised feature learning and deep learning tutorial. http://ufldl.stanford.edu/tutorial/ (Accessed July 10, 2021).
   Google Scholar
• Pennsylvania Department of Transportation (PDOT), 2021. Highway safety program guide. Harrisburg. PA.
   Google Scholar
• Pérez-Acebo, H., Gonzalo-Orden, H., and Rojí, E, 2019. Skid resistance prediction for new two-lane roads. Proceedings of the Institution of Civil Engineers – Transport, 172 (5), 264–273. https://doi.org/10.1680/jtran.17.00045.
   Web of Science ®Google Scholar
• PIARC, 1995. International PIARC experiment to compare and harmonize texture and skid resistance measurements. Report NO. AIPCR-01-040.T. PIARC, Brussels, Belgium.
   Google Scholar
• Shad and Ahmad, 2019. Road infrastructure analysis with reference to traffic stream characteristics and accidents: An application of benchmarking based safety analysis and sustainable decision-making. Applied Sciences, 9, 2320. https://doi.org/10.3390/app9112320.
   Google Scholar
• Simonyan, K., and Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs.CV].
   Google Scholar
• Sitaula, C., and Hossain, M.B, 2021. Attention-based VGG-16 model for COVID-19 chest X-ray image classification. Appplied Intelligence, 51, 2850–2863. https://doi.org/10.1007/s10489-020-02055-x.
   PubMed Web of Science ®Google Scholar
• Ueckermann, A., et al., 2015. A contribution to non-contact skid resistance measurement. International Journal of Pavement Engineering, 16 (7), 646–659. DOI: 10.1080/10298436.2014.943216.
   Web of Science ®Google Scholar
• Wang, K.C.P., et al., 2015. Network level pavement evaluation with 1-mm 3D survey system. Journal of Traffic and Transportation Engineering (English Edition, 2 (6), 391–398. https://doi.org/10.1016/j.jtte.2015.10.005.
   Google Scholar
• Wang, Y., et al., 2019. Enhancing transportation systems via deep learning: A survey. Transportation Research Part C, 99, 144–163.
   Web of Science ®Google Scholar
• Wix, R, 2017. Using a 3D system for measuring pavement macro-texture. The 5th International Safer Roads Conference, Auckland, New Zealand. https://saferroadsconference.com/wp-content/uploads/2017/06/1330_4-Richard-Wix-Safer-Roads-Conference-Presentation-2017-Richard-Wix.pdf (Accessed April 8, 2021).
   Google Scholar
• World Health Organization, 2018. Global status report on road safety 2018: Summary. Geneva. Switzerland.
   Google Scholar
• Yang, G., et al., 2018. Convolutional neural network–based friction model using pavement texture data. Journal of Computing in Civil Engineering, 32 (6), 04018052.
   Web of Science ®Google Scholar
• Yang, G., et al., 2019. Random Forest–based pavement surface friction prediction using high-resolution 3D image data. Journal of Testing and Evaluation, 49, 2. doi:10.1520/JTE20180937.
   Web of Science ®Google Scholar
• Yang, G., et al., 2021. Automatic pavement type recognition for image-based pavement condition survey using convolutional neural network. Journal of Computing in Civil Engineering, 35 (1), 04020060.
   Web of Science ®Google Scholar
• Zhan, Y., et al., 2020. Friction-ResNets: Deep residual network architecture for pavement skid resistance evaluation. J. Transp. Eng. Part B: Pavements, 146 (3), 04020027.
   Web of Science ®Google Scholar
• Zhang, A., et al., 2019. Automated pixel-level pavement crack detection on 3D asphalt surfaces with a recurrent neural network. Computer-Aided Civil and Infrastructure Engineering, 34, 213–229.
   Web of Science ®Google Scholar
• Zou, Y., Yang, G., and Cao, M, 2021. Neural network-based prediction of sideway force coefficient for asphalt pavement using high-resolution 3D texture data. International Journal of Pavement Engineering, DOI: 10.1080/10298436.2021.1884862.
   Web of Science ®Google Scholar
• Zuniga-Garcia, N., and Prozzi, J.A, 2019. High-definition field texture measurements for predicting pavement friction. Transportation Research Record, DOI: 10.1177/0361198118821598.
   PubMed Web of Science ®Google Scholar