Learning Pedestrian Dynamics from the Real World

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.

• Type: Conference
• Year: 2009
• Where: ICCV
• Authors: Paul Scovanner, Marshall Tappen
• Keywords: Computer Vision, ICCV 2009, Pedestrian Dynamics