中央研究院 資訊科學研究所

In this presentation, I will introduce what is Internet-of-Vehicles (IoV), including of its history, current status, and future applications first. After that, an IoV project of "context-based micro-navigation” will be presented. Compared to the traditional navigation system, which provides macro-navigation instructions based on the information collected from the driver’s own car, the context-based micro-navigation system can provide micro-navigation instructions based on IoV-integrated context information. Hopefully, both the safety margin and driving efficiency can be increased with the help of the IoV-based micro-navigation system.

        Finally, a vision-based ego-positioning method for IoV will be presented. We have shown that sub-meter accuracy can be achieved with low cost monocular cameras. This is a significant accomplishment compared to GPS with the precision around 3 to 20 meters. For example, the sub-meter accuracy makes the left and right lanes identifiable in a multi-lane road, which is important for the implementation of micro navigation in an IoV system. It also enables the distinguishability of the elevated road and ground level road when they share the same ground-level location.

Kuan-Wen Chen is an assistant professor in Department of Computer Science at National Chiao Tung University, Hsinchu, Taiwan. He received the B.S. degree in computer and information science from National Chiao Tung University, Hsinchu, Taiwan, in 2004, and the Ph.D. degree in computer science and information engineering from National Taiwan University, Taipei, Taiwan, in 2011. He was an postdoc researcher (from 2012 to 2014) and an assistant research fellow (from 2014 to 2015) in Intel-NTU Connected Context Computing Center at National Taiwan University, Taipei, Taiwan. His current research interests include computer vision, pattern recognition, multimedia, and internet-of- vehicles.