Distinction of winter road surface conditions using road surveillance camera

Takeuchi, Kazuhiko; Kawai, Shohei; Shibata, Katsunari; Horita, Yuukou

doi:10.1109/itst.2012.6425264

Cited by 8 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to recent developments in the Intelligent Transportation System (ITS), it became more convenient to determine highway surface conditions using camera-based monitoring systems. Takeuchi et al collected 91 images of a highway surface using road surveillance cameras, then they used the pixel intensity histogram to determine five texture features, including mean, contrast, variance, energy, and entropy (Takeuchi et al 2012). They used the K-Means algorithm for clustering those images and achieved an accuracy rate of 84.8% in daytime conditions.…”

Section: Literature Reviewmentioning

confidence: 99%

Winter road surface condition classification using convolutional neural network (CNN): visible light and thermal image fusion

Zhang¹,

Nateghinia²,

Miranda-Moreno³

et al. 2022

Can. J. Civ. Eng.

View full text Add to dashboard Cite

In winter, road conditions play a crucial role in traffic flow efficiency and road safety. Icy, snowy, slushy, or wet road conditions reduce tire friction and affect vehicle stability which could lead to dangerous crashes. To keep traffic operations safe, cities spend a significant budget on winter maintenance operations such as snow plowing and spreading salt/sand. This paper proposes a methodology for automated winter road surface conditions classification using Convolutional Neural Network and the combination of thermal and visible light cameras. As part of this research, 4,244 pairs of visible light and thermal images are captured from pavement surfaces and classified into snowy, icy, wet, and slushy surface conditions. Two single-stream CNN models (visible light and thermal streams), and one dual-stream CNN model are developed. The average F1-Score of dual-stream model is 0.866, 0.935, 0.985, and 0.888 on snowy, icy, wet, and slushy, respectively. The weighted average F1-Score is 0.94.

show abstract

Section: Literature Reviewmentioning

confidence: 99%