Research on Crowd Behavior Based on the Velocity Field

DOI

10.2991/nceece-15.2016.167How to use a DOI?

Keywords

crowd behavior; velocity field; Gaussian filter; Horn-Schunck algorithm; interpolation function.

Abstract

Data-driven modeling method has become an ideal research method in crowd behavior simulation fields. The basic idea of data-driven modeling method is that velocity field generated by the crowd behavior characteristic information. Because of the video data acquisition, the velocity field has its limitation, namely virtual crowd simulation scenario should be consistent with the crowd scene of video data. So we present an optimization strategy: first, it eliminates velocity of scene from the generated velocity field; And second, it constructs velocity field by interpolation again. Experiments show that the presented optimization strategy can design the velocity field without scene information, and it is helpful to improve the universality of the velocity field.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fang Yuan
AU  - Ke Ma
AU  - Jia-hong Liang
AU  - Yong-Jing Chao
PY  - 2015/12
DA  - 2015/12
TI  - Research on Crowd Behavior Based on the Velocity Field
BT  - Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering
PB  - Atlantis Press
SP  - 922
EP  - 930
SN  - 2352-5401
UR  - https://doi.org/10.2991/nceece-15.2016.167
DO  - 10.2991/nceece-15.2016.167
ID  - Yuan2015/12
ER  -