The University of Minnesota has been selected by the Toyota Research Institute (TRI) as one of 13 additional academic institutions that will participate in the next five-year phase of a collaborative research program. These universities join MIT, Stanford, and the University of Michigan, which have worked with TRI over the last five years to expand the body of research into artificial intelligence (AI) with the goal of amplifying the human experience.
Assistant Professor Hyun Soo Park in the Department of Computer Science and Engineering will lead the TRI-sponsored research at the University of Minnesota. Park specializes in image processing and computer vision and will bring this expertise to the collaborative. Park and his colleague Professor Jianbo Shi of the University of Pennsylvania will be developing datasets and researching high-fidelity models for in-cabin behavior understanding. This work will focus on enabling the measurement, analysis, and prediction of the behaviors of drivers and passengers to increase safe driving.
“The behavioral state of drivers and passengers in cars, for example, sleepiness and social interactions, play a major role of safe driving,” Park said.
Park’s team will create a data acquisition system for the collection of large-scale in-cabin video datasets, using a multiview camera system that can allow the capture of realistic on-site human behavior at multiple resolutions, including:
- Close-up facial expression, head pose, and eye gaze
- Hand and arm movements and gestures
- Upper body movements and interaction
With this dataset, the researchers will develop robust and generalizable algorithms for the 4D space-time representation of behaviors.
TRI will be investing more than $75 million in the academic institutions over the next five years.
(Adapted from a news release posted by the University of Minnesota's College of Science and Engineering on January 26, 2021.)