An Edge-computing System for Observing Road Surface Condition and Visibility in Winter Road

Date and Time: Wednesday, May 10, 2023: 8:20 AM - 10:00 AM
Location: Keck 100

 

Lead Presenter:  Sho Takahashi, Associate Professor
Affiliation:  Hokkaido University
Social Media Handle:  Sho

Lead Presenter Biography

Dr. Sho Takahashi has been a full-time Associate Professor in the Faculty of Engineering, Hokkaido University, Japan, since April 2018. He received his B.S., M.S. and Ph.D. degrees in Electronics and Information Engineering from Hokkaido University, Japan in 2008, 2010 and 2013, respectively. He joined the Graduate School of Information Science and Technology, Hokkaido University, as an Assistant Professor in 2013. He was an Associate Professor of the Education and Research Center for Mathematical and Data Science, Hokkaido University from 2017 to 2018. He is a visiting researcher of Media Integration and Communication Center, University of Florence from 2018 to 2019. He is currently an Associate Professor in the Faculty of Engineering, Hokkaido University. His research interests include semantic analysis and visualization in various data and application. He is a member of the IEEE, IEICE, Institute of Image Information and Television Engineers (ITE), Japan Society of Civil Engineering (JSCE), Society of Automotive Engineering of Japan (JSAE), Japan Society of Traffic Engineers (JSTE) and Japan Association for Human and Environmental Symbiosis (JAHES). 

Co-Authors

Masahiro Yagi, Doctoral Course Student, Graduate School of Engineering, Hokkaido University; Toru Hagiwara, Professor, Faculty of Engineering, Hokkaido University

Presentation Description 

In Hokkaido, Japan, there are numerous road closures due to blowing snow and snow drifts on the roads every winter season. In addition, traffic accidents occur because of icy or snowy/icy road surfaces. These severe winter road conditions often result in multi-vehicle crashes and significant economic loss in winter. In order to approach for reducing the above problems, we developed the edge-computing system for accumulating visibility and the road surface condition in winter road. This system was developed to store driving video images took by the onboard video camera and to compute WIPS and the road surface condition based on Mobile Nets. In addition, some stored data which are recorded video images, WIPS, the estimated road surface condition and GNSS data, are transmitted to the server system in real-time. All of these functions were operated on the microcomputer as realizing the edge-computing system which is automatically operated in the intercity bus actually. The system successfully operated the image extraction system and the data transmitting function through the 2021-2022 winter season. All data during one winter season were accumulated, and it is possible to use for future study to improve the road and transportation management in this research area.

Extended Summary

Extended Abstract

Download Extended Abstract PDF 

Presentation Video