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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICCV.2009.5459224 | ICCV |
Keywords | DocType | Volume |
predictive models,computational modeling,motion estimation,upper bound,optimization,learning artificial intelligence,tracking,force | Conference | 2009 |
Issue | ISSN | ISBN |
1 | 1550-5499 E-ISBN : 978-1-4244-4419-9 | 978-1-4244-4419-9 |
Citations | PageRank | References |
38 | 2.03 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paul Scovanner | 1 | 730 | 23.87 |
Marshall F. Tappen | 2 | 1901 | 89.34 |