Title :
Learning pedestrian dynamics from the real world
Author :
Scovanner, Paul ; Tappen, Marshall F.
Author_Institution :
Univ. of Central Florida, Orlando, FL, USA
fDate :
Sept. 29 2009-Oct. 2 2009
Abstract :
In this paper we describe a method to learn parameters which govern pedestrian motion by observing video data. Our learning framework is based on variational mode learning and allows us to efficiently optimize a continuous pedestrian cost model. We show that this model can be trained on automatic tracking results, and provides realistic and accurate pedestrian motions.
Keywords :
learning (artificial intelligence); motion estimation; pedestrian dynamics; variational mode learning; video data obseravtion; Computer vision; Cost function; Event detection; Large-scale systems; Layout; Learning systems; Predictive models; Tracking; Videoconference; Virtual environment;
Conference_Titel :
Computer Vision, 2009 IEEE 12th International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4244-4420-5
Electronic_ISBN :
1550-5499
DOI :
10.1109/ICCV.2009.5459224
