Introducing “LISA”:
Making of Smart and Safe Automobiles
Dr. Mohan Trivedi
Computer Vision and Robotics Laboratory
University of California, San Diego
Date: Friday, May 6, 2005
Place: Engineering Sciences Building, Room 2001
Time: 2:00 pm — 3:00 pm
Abstract:
“Smart” (or Intelligent) environments are supposed to assist
humans to accomplish their goals, with enhanced safety, efficiency, effectiveness,
and convenience. Such spaces need to capture and maintain an awareness
of the static and dynamic states of the space and its inhabitants. Automobiles
provide an interesting and challenging domain for research as well as
applications of Intelligent Environment and associated technologies. Computer
vision is recognized as a core discipline to realize such capabilities
for observing humans in smart spaces so that appropriate actions can be
taken in a reliable, efficient, and robust manner. Constraints imposed
by the “real-world” make development of such systems a challenging
task. In this presentation, we will provide a systems-oriented framework
and roadmap for examining automobile-based intelligent environments. We
will consider three main components of the system, driver, vehicle, and
vehicle surround. We will discuss various issues and ideas for developing
models for these main components as well as that of the complex task of
safe driving. The presentation will include discussion of novel sensory
systems and algorithms for capturing not only the dynamic surround information
of the vehicle but also the state, intent and behavior patterns of drivers.
Publications and Video Demonstrations can be found at website for LISA:
Laboratory for Intelligent and Safe Automobiles http://cvrr.ucsd.edu/LISA/
MOHAN TRIVEDI is a Professor in the Electrical and Computer
Engineering Department at UC San Diego and serves as the Director of the
Computer Vision and Robotics Research Laboratory (http://cvrr.ucsd.edu).
He and his team are engaged in a broad range of research studies, which
include active perception and novel machine vision systems, intelligent
("smart") environments, distributed video networks and intelligent
systems. His team's recent research involvement and accomplishments include:
a new framework for efficient means of extraction and integration of multiple
depth cues; a novel multimodal interface for modeling and monitoring composition
and activity in an "intelligent room", development of cooperating
mobile robot teams; computational models for texture analysis and synthesis;
an integrated robotic system for applications in nuclear environments
and for inspection and maintenance of high-speed railway (Shinkansen)
tracks; a real time machine vision system for detection and classification
of very small marine organisms in the ocean; and a distributed intelligent
system for traffic incidence monitoring and mitigation. He has been published
extensively and has edited over a dozen volumes including books, special
issues, video presentations, and conference proceedings. Trivedi serves
on the Executive Committee of the California Institute for Telecommunication
and Information Technologies (Cal-(IT)2) (http://www.calit2.net/) as the
leader of the Intelligent Transportation and Telematics Team. He also
serves as a charter member of the Executive Committee of the University
of California System wide Digital Media Innovation Program (DiMI) (http://www.dimi.ucsb.edu/).
He serves regularly as a consultant to industry and government agencies
in the USA and abroad.
Host: B.S. Manjunath, Professor of Electrical and Computer Engineering
