revision_2.pdf (22.2 MB)
Download file

Evidential event inference in transport video surveillance

Download (22.2 MB)
journal contribution
posted on 16.02.2018, 09:09 by Xin Hong, Yan Huang, Wenjun Ma, Sriram Varadarajan, Paul Miller, Weiru Liu, Maria Jose Santofimia Romero, Jesus Martinez del Rincon, Huiyu Zhou
This paper presents a new framework for multi-subject event inference in surveillance video, where measurements produced by low-level vision analytics usually are noisy, incomplete or incorrect. Our goal is to infer the composite events undertaken by each subject from noise observations. To achieve this, we consider the temporal characteristics of event relations and propose a method to correctly associate the detected events with individual subjects. The Dempster–Shafer (DS) theory of belief functions is used to infer events of interest from the results of our vision analytics and to measure conflicts occurring during the event association. Our system is evaluated against a number of videos that present passenger behaviours on a public transport platform namely buses at different levels of complexity. The experimental results demonstrate that by reasoning with spatio-temporal correlations, the proposed method achieves a satisfying performance when associating atomic events and recognising composite events involving multiple subjects in dynamic environments.

Funding

This work has been in part supported by UK EPSRC under Grants EP/G034303/1 and EP/N508664/1. Dr. H. Zhou is also supported by UK EPSRC under Grant EP/N011074/1.

History

Citation

Computer Vision and Image Understanding, 2016, 144, pp. 276-297 (22)

Author affiliation

/Organisation

Version

AM (Accepted Manuscript)

Published in

Computer Vision and Image Understanding

Publisher

Elsevier for Academic Press

issn

1077-3142

eissn

1090-235X

Acceptance date

06/10/2015

Copyright date

2016

Available date

16/02/2018

Publisher version

https://www.sciencedirect.com/science/article/pii/S1077314215002477?via=ihub

Notes

Supplementary material associated with this article can be found, in the online version, at 10.1016/j.cviu.2015.10.017. This is open data under the CC BY license http://creativecommons.org/licenses/by/4.0/

Language

en