Urban Digital Twins for Intelligent Road Inspection Seminar
About
Infrastructure maintenance has entered a new era. The rapid development of Artificial Intelligence (AI) technologies, such as machine learning, big data, high-performance computing, data fusion, and computer vision, has revolutionized current infrastructure maintenance systems by making them intelligent and self-aware. Furthermore, as the Internet of Things (IoT) began to emerge, it saw the introduction of digital twins along with the numerous benefits they bring to industries, especially in terms of cost-effectiveness and ease of use. The conceptualization of the smart city through digital twins is evident. From urban planning to land-use optimization, it has the power to govern the city effectively. Urban digital twins (UDT) - defined as the application of digital twin technology to cities - is recognized as an opportunity to upgrade urban planning and develop smart cities.
AI and UDT technologies are expected to offer new opportunities for current transportation infrastructures and systems in terms of their evaluation and maintenance and will make such systems intelligent and self-sustaining in the future. Intelligent road inspection is becoming increasingly important due to a drastic increase in the number of vehicles and consequently road usage. The success of a road transport system is inherently dependent on the riding quality and comfort level of the users, for which timely detection of faults and ensuing maintenance are of utmost importance. The current manual observation and detection methods are cumbersome, time-consuming, and expensive. Therefore, in order to warrant long-standing structural integrity and safety levels, future transportation maintenance systems need to integrate innovative technologies that will employ next-generation distributed sensors and vision-based AI approaches to help in the evaluation, classification, and localization of road distresses in a timely and cost-effective manner.
Speakers
TBD
Chairs
Rui Fan
Tongji University
rui.fan@ieee.org
Mohammud Junaid Bocus
University of Bristol
junaid.bocus@bristol.ac.uk
Yu Jiang
ClearMotion
yjiang@clearmotion.com
Program Committee
Qijun Chen
Tongji University
Wenshuo Wang
McGill University
Yanting Zhang
Donghua University
Xingyi Zhu
Tongji University
Sicen Guo
Tongji University
Yi Feng
Tongji University
Shuai Su
Tongji University
Jiahang Li
Tongji University
Submission Instructions
Call for papers
Research papers are solicited in, but not limited to, the following topics:
Big data for road condition assessment;
Self/un-supervised machine learning approaches for intelligent road inspection;
Real-time deep learning inference for intelligent road inspection;
Multi-modal 3D modeling for urban digital twin.
Important Dates
Nov. 01, 2022: Due date for full workshop papers submission
Nov. 16, 2022: Notification of paper acceptance to authors
Nov. 25, 2022: Camera-ready of accepted papers
Submission Guidelines
Please submit a full-length paper (up to 10 pages in IEEE two-column format, including references) through the online workshop submission system: https://wi-lab.com/cyberchair/2022/bigdata22/scripts/ws_submit.php.
Papers should be formatted as per the IEEE Computer Society Proceedings Manuscript Formatting Guidelines: