Evidential event inference in transport video surveillance
No disponemos de la información de contacto de este autor.
No disponemos de la información de contacto de este autor.
No disponemos de la información de contacto de este autor.
No disponemos de la información de contacto de este autor.
No disponemos de la información de contacto de este autor.
No disponemos de la información de contacto de este autor.
Computer Architecture and Networks Group, University of Castilla-La Mancha, Ciudad Real, Spain
MariaJose.Santofimia@uclm.es
No disponemos de la información de contacto de este autor.
No disponemos de la información de contacto de este autor.
CONFERENCE — Computer Vision and Image Understanding
PAGES — 276-297
ISSN — 1077-3142
VOLUME — 144
DOI — 10.1016/j.cviu.2015.10.017
PUBLISHER — Elsevier
YEAR — 2016
@article{hong2016evidential,
title={Evidential event inference in transport video surveillance},
author={Hong, Xin and Huang, Yan and Ma, Wenjun and Varadarajan, Sriram and Miller, Paul and Liu, Weiru and Romero, Maria Jose Santofimia and del Rincon, Jesus Martinez and Zhou, Huiyu},
journal={Computer Vision and Image Understanding},
volume={144},
pages={276--297},
year={2016},
publisher={Elsevier}
}
Abstract
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.