Title
Learning Pedestrian Dynamics From The Real World
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. ©2009 IEEE.
Publication Date
12-1-2009
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Number of Pages
381-388
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICCV.2009.5459224
Copyright Status
Unknown
Socpus ID
77953186524 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/77953186524
STARS Citation
Scovanner, Paul and Tappen, Marshall F., "Learning Pedestrian Dynamics From The Real World" (2009). Scopus Export 2000s. 11385.
https://stars.library.ucf.edu/scopus2000/11385