Abstract
In 2020, there was a record heavy snowfall owing to climate change. In reality, 2,000 vehicles were stuck on the highway for three days. Because of the freezing of the road surface, 10 vehicles had a billiard accident. Road managers are required to provide indicators to alert drivers regarding snow cover at hazardous locations. This study proposes a deep learning application with live image post-processing to automatically calculate a snow hazard ratio indicator. First, the road surface hidden under snow is translated using a generative adversarial network, pix2pix. Second, snow-covered and road surface classes are detected by semantic segmentation using DeepLabv3+ with MobileNet as a backbone. Based on these trained networks, we automatically compute the road to snow rate hazard index, indicating the amount of snow covered on the road surface. We demonstrate the applied results to 1,155 live snow images of the cold region in Japan. We mention the usefulness and the practical robustness of our study.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
National Institute for Land and Infrastructure Management, “Snow and Cold Region Traffic Accident Survey and Policy”, Research Report, pp. 3–10 (2003)
Saskatchewan Professional Driver’s Handbook, pp. 136–139. Saskatchewan Publication (2019)
Loce, R.P., Bernal, E.A., Wu, W., Bala, R.: Computer vision in roadway transportation system: a survey. J. Electr. Imaging 22(4), 041121 (2013)
Takahashi, T., Tokunaga, R., Sato, K., et al.: A Study on Development of Prediction Method for Winter Road Surface Corresponding to Change of Snow Removal Level (2012–2015)
University of Waterloo: “Machine Vision Assisted Winter Road Condition Monitoring”, Technology Summary, 8810-7336
Pan, G., Fu, L., Yu, R., Muresan, M.: Winter Road Surface Condition Recognition Using a Pre-trained Deep Convolutional Neural Netwrok
Zhao, J., Wu, H., Chen, L.: Road surface state recognition based on SVM optimization and image segmentation processing. J. Adv. Transp. 2017, Article Id 6458495, Hindawi (2017)
Sabanovic, E., Zuraulis, V., Prentkovskis, O., Skrickij, V.: Identification of road surface type using deep neural networks for friction coefficient estimation. Sensors 2020, 20,612 (2020)
Padarthy, M., Heyns, E.: Identification and classification of slippery winter road conditions using commonly available vehicle variables. Transp. Res. Rec. 2673(2), 60–70 (2019)
Nagata, Y., Kaneda, Y., Echigo, K., et al.: Potential of snow drift estimation by using CCTV camera images. In: JSSI & JSSE Joint Conference, Nagoya (2016)
Basavaraju, J., Du, F.Z., Ji, J.: A machine learning approach to road surface anomaly assessment using smartphone sensors. IEEE Sens. J. 20(5), 2635–2647 (2020)
Carrillo, J., Crowley, M.: Integration of roadside camera images and weather data for monitoring winter road surface conditions. In: Canadian Association of Road Safety Professionals CARSP Conference, (2019)
Grabowski, D., Czyzewski, A.: System for monitoring road slippery based on CCTV cameras and convolutional neural networks. J. Intell. Inf. Syst. 55, 521–534 (2020)
Liang, C., Ge, J., Zhang, W., Gui, K., Cheikh, F.A., Ye, L.: Winter road surface status recognition using deep semantic segmentation network. In: International Workshop on Atmospheric Icing Structures (2019)
Isola, P., et al.: Image-to-image translation with conditional adversarial network. In: CVPR (2017)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 640–651 (2017)
Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017)
Chen, L.C., Papandreou, G., Kokkinos, I., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834–848 (2018)
Ministry of Land, Infrastructure, Transport and Tourism, the live camera images of each region office activities in Japan. https://www.mlit.go.jp/road/road_e/index_e.html
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice Hall (2008)
Foster, D.: Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play. O’reilly (2019)
Yasuno, T., Fujii, J., Amakata, M.: Pop-outs segmentation for concrete prognosis indices using UAV monitoring and dense dilated convolutions. In: International Workshop on Structural Health Monitoring, Stanford, CA (2019)
Acknowledgments
I would like to thank Takuji Fukumoto and Shinichi Kuramoto (MathWorks) for providing us MATLAB resources for deep learning frameworks.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yasuno, T., Sugawara, H., Fujii, J. (2022). Road Surface Translation Under Snow-Covered and Semantic Segmentation for Snow Hazard Index. In: Takama, Y., et al. Advances in Artificial Intelligence. JSAI 2021. Advances in Intelligent Systems and Computing, vol 1423. Springer, Cham. https://doi.org/10.1007/978-3-030-96451-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-96451-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96450-4
Online ISBN: 978-3-030-96451-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)