Document Type

Journal Article

Department/Unit

Department of Computer Science

Title

Object motion detection using information theoretic spatio-temporal saliency

Language

English

Abstract

This paper proposes to employ the visual saliency for moving object detection via direct analysis from videos. Object saliency is represented by an information saliency map (ISM), which is calculated from spatio-temporal volumes. Both spatial and temporal saliencies are calculated and a dynamic fusion method developed for combination. We use dimensionality reduction and kernel density estimation to develop an efficient information theoretic based procedure for constructing the ISM. The ISM is then used for detecting foreground objects. Three publicly available visual surveillance databases, namely CAVIAR, PETS and OTCBVS-BENCH are selected for evaluation. Experimental results show that the proposed method is robust for both fast and slow moving object detection under illumination changes. The average detection rates are 95.42 % and 95.81 % while the false detection rates are 2.06 % and 2.40 % in CAVIAR (INRIA entrance hall and shopping center) dataset and OTCBVS-BENCH database, respectively. The average processing speed is 6.6 fps with frame resolution 320 × 240 in a typical Pentium IV computer. © 2009 Elsevier Ltd. All rights reserved.

Keywords

Foreground detection, Moving object detection

Publication Date

2009

Source Publication Title

Pattern Recognition

Volume

42

Issue

11

Start Page

2897

End Page

2906

Publisher

Elsevier

DOI

10.1016/j.patcog.2009.02.002

ISSN (print)

00313203

This document is currently not available here.

Share

COinS