International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Developing a Solution to Improve Road Safety Using Multiple Deep Learning Techniques

  • Received : 2022.12.10
  • Accepted : 2022.12.14
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The number of traffic accidents caused by wet or icy road surface conditions is on the rise every year. Car crashes in such bad road conditions can increase fatalities and serious injuries. Historical data (from the year 2016 to the year 2020) on weather-related traffic accidents show that the fatality rates are fairly high in Korea. This requires accurate prediction and identification of hazardous road conditions. In this study, a forecasting model is developed to predict the chances of traffic accidents that can occur on roads affected by weather and road surface conditions. Multiple deep learning algorithms taking into account AlexNet and 2D-CNN are employed. Data on orthophoto images, automatic weather systems, automated synoptic observing systems, and road surfaces are used for training and testing purposes. The orthophotos images are pre-processed before using them as input data for the modeling process. The procedure involves image segmentation techniques as well as the Z-Curve index. Results indicate that there is an acceptable performance of prediction such as 65% for dry, 46% for moist, and 33% for wet road conditions. The overall accuracy of the model is 53%. The findings of the study may contribute to developing comprehensive measures for enhancing road safety.

Keywords

Acknowledgement

This research was financially supported by the Ministry of Trade, Industry, and Energy (MOTIE), and the Korea Institute for Advancement of Technology (KIAT) through the International Cooperative R&D program. (Grant Number: P0005449)

References

  1. Seunghyun Kim, Kang-Hwa Kim, Min-Woo Lee, Yeoan-Joo Cho, Yukeun Hahm "Improving vehicle safety through road surface condition and weather data analysis" Journal of Information Technology and Architecture, Vol.38, No.1, pp 1-13, 2016. 
  2. Lee. Minwoo, Kim. Younggon, Jun. Yongjoo, Shin. Yeongho "Random Forest-based Prediction of Road Surface Condition Using Spatio-Temporal Features." J. Korean Soc. Transp, Vol.37, No.4, pp.338-349, 2019 DOI: https://doi.org/10.7470/jkst.2019.37.4.338 
  3. KIM. Younggon, LEE. Minwoo, YUN. Yeojeong, JUN. Yongjoo, KIM. KwangSik "Development of a Forecasting Model for Traffic Accident Probability on Icy Roads Using Deep Learning" J. Korean Soc. Transp, Vol.40, No.1, pp.111-127, 2022. DOI: https://doi.org/10.7470/jkst.2022.40.1.111 
  4. YeonJu Jo, "A Study of Real-Time Big Data Analysis and System for Predicting Surface Condition" Master Thesis. Konguk University, Seoul, South Korea, 2018.
  5. JongHoon Kim, Jae Moo Won "A Development of the Road Surface Decision Algorithm Using support vector machine (Support Vector Machine) Clustering Methods" The Korea Institute of Intelligent Transport Systems, Vol.12, No.5, pp.01-12, 2013. DOI: https://doi.org/10.12815/kits.2013.12.5.001 
  6. Traffic Accident Analysis System http://taas.koroad.or.kr/sta/acs/gus/selectStaInfoGraph.do?menuId=WEB_KMP_IDA_TAI 
  7. Siu-Wing Cheng, Tamal K. Dey, Jonathan Shewchuk, "Delaunay Mesh Generation", Chapman and Hall/CRC, pp 31-54, 2013. 
  8. Korea Meteorological Administration https://data.kma.go.kr/resources/html/en/aowdp.html 
  9. Takahiro Tsubotaa, Celso Fernando, Toshio Yoshiia, Hirotoshi Shirayanagia "Effect of Road Pavement Types and Ages on Traffic Accident Risks" Transportation Research Procedia, Vol.34, pp 211-218, 2018. DOI: https://doi.org/10.1016/j.trpro.2018.11.034 
  10. Eunjin Oh, Hee-Kap Ahn, "Voronoi Diagrams for a Moderate-Sized Point-Set in a Simple Polygon Institute for Information & communications Technology Promotion, 2018. DOI: https://arxiv.org/pdf/1801.02292.pdf 
  11. D. T. Lee2, B. J. Schacht "Two Algorithms for Constructing a Delaunay Triangulation" International Journal of Computer and Information Sciences, Vol.9, No.3, 1980. DOI: https://doi.org/10.1007/BF00977785 
  12. Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton "ImageNet Classification with Deep CNNs." 2012. DOI: https://doi.org/10.1145/3065386 
  13. Soroush Ameli, "Road Condition Sensing Using deep learning and Wireless Signals", Master Thesis. University of Waterloo, Ontario, Canada, 2020.
  14. Sohini Roychowdhury, Minming Zhao, Andreas Wallin, Niklas Ohlsson, MatsJonasson, "Machine Learning Models for Road Surface and Friction Estimation using Front-Camera Images", International Joint Conference on Neural Networks (IJCNN), 2018. DOI: https://doi.org/10.1109/IJCNN.2018.8489188
  15. Yao Ma, Meizhu Wang, Qi Feng, Zhiping He, Mi Tian, "Current Non-Contact Road Surface Condition Detection Schemes and Technical Challenges", MDPI (Sensors), Vol.22, 2022. DOI: https://doi.org/10.3390/s22249583 
  16. Tanita Fossli Brustad, Aleksander Pedersen, Borre Bang, "A field study of sensors for winter road assessment", Elsevier, Vol.7, 2020. DOI: http://dx.doi.org/10.1016/j.trip.2020.100206 
  17. Jinhwan Yoo, Chang-Hun Lee, Hae-Min Jea, Sang-Kwon Lee, Youngsam Yoon, Jaehun Lee, Kiho Yum, Seoung-Uk Hwang, "Classification of Road Surfaces Based on convolutional neural network Architecture and Tire Acoustical Signals", MDPI (Applied Sciences), Vol.12, 2022. DOI: https://doi.org/10.3390/app12199521 
  18. Jiandong Zhao, Hongqiang Wu, Liangliang Chen, "Road Surface State Recognition Based on support vector machine Optimization and Image Segmentation Processing", Journal of Advanced Transportation (Hindawi), Vol.2017, 2017. DOI: https://doi.org/10.1155/2017/6458495 
  19. Guangyuan Pan, Liping Fu, Ruifan Yu, Matthew Muresan, "Winter Road Surface Condition Recognition Using a Pre-Trained Deep CNN", Transportation Research Board 97th Annual Meeting, Vol.49, No.4, 2018. DOI: https://doi.org/10.1139/cjce-2020-0613 
  20. Pan Guangyuan, Muresan Matthew, Yu Ruifan, Fu Liping, "Real-time Winter Road Surface Condition Monitoring Using an Improved Residual CNN", Canadian Journal of Civil Engineering, Vol.49, No.4, 2019. DOI: https://doi.org/10.1139/cjce-2019-0367 
  21. Sang Hyuk Lee, Hye-Jin Cho, "A Study on Safety Impacts for VMS Traffic Information", The Korea Institute of Intelligent Transport Systems, Vol.14, No.1, pp 22-30, 2015. DOI: http://dx.doi.org/10.12815/kits.2015.14.1.022