University of Cambridge > Talks.cam > Computer Laboratory Opera Group Seminars > Vehicular Sensing

Vehicular Sensing

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Pedro Brandao.

Slides available .

Abstract:

Land survey data is currently acquired through a variety of methods, ranging from fixed-station based (e.g. weather stations) to mobile systems (e.g polar orbiting Earth observation satellites). A typical characteristic of such sensing systems is its ability to send data in real-time, whether it is a temperature reading or a multispectral scanner image, through some type of communication network. The advent of a wireless communication network supported by vehicles, in the form of a vehicular ad hoc network (VANET), can provide real-time access to the variety of sensors that production cars typically have, creating a powerful new mean of land survey data acquisition. Such vehicular satellites, which follow complex orbits spanning the road network, are able to monitor variables such as the geometry, topology and traffic rules of these roads, their real-time mobility, outside temperature, carbon-dioxide concentration, rain, pavement degradation and adherence, or radio coverage (WiFi, cellular, etc). Furthermore, new and sophisticated sensors are being proposed and installed in production cars, such as high-resolution windshield cameras, capable of interpreting traffic signs, which greatly enhance the monitoring capacity of vehicular sensing.

In this talk we will present the work we have been developing around the subject of vehicular sensing and vehicular ad hoc networks. We will present the DIVERT VANET simulator and the results from connectivity analysis of such networks in urban environments. We will discuss two main applications of vehicular sensing: automatic construction of maps of the road network and collaborative localization of vehicles through a vision-enabled VANET .

Bio:

Dr. Ferreira is an assistant professor at the Computer Science Department of the School of Sciences of University of Porto. His research interests evolved from the implementation of logic programming systems, where he has been contributing on the development team of the Yap Prolog System (the MYDDAS deductive database module), to the area of logic-based spatial databases and spatial networks. He has been leading several research projects in the areas of deductive databases, vehicular networks and advanced spatial database systems. He is currently the PI of a joint research project between University of Porto and Carnegie Mellon University, DRIVE -IN (Distributed Routing and Infotainment through VEhicular Inter-Networking), which is deploying a VANET testbed of 500 taxis in the city of Porto. NDRIVE company, a competitor of TomTom and Garmin, is the industrial partner of this project.

This talk is part of the Computer Laboratory Opera Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity