Deakin University
Browse

File(s) under permanent embargo

Multiple-object tracking in cluttered and crowded public spaces

conference contribution
posted on 2010-01-01, 00:00 authored by R Martin, Ognjen Arandjelovic
This paper addresses the problem of tracking moving objects of variable appearance in challenging scenes rich with features and texture. Reliable tracking is of pivotal importance in surveillance applications. It is made particularly difficult by the nature of objects encountered in such scenes: these too change in appearance and scale, and are often articulated (e.g. humans). We propose a method which uses fast motion detection and segmentation as a constraint for both building appearance models and their robust propagation (matching) in time. The appearance model is based on sets of local appearances automatically clustered using spatio-kinetic similarity, and is updated with each new appearance seen. This integration of all seen appearances of a tracked object makes it extremely resilient to errors caused by occlusion and the lack of permanence of due to low data quality, appearance change or background clutter. These theoretical strengths of our algorithm are empirically demonstrated on two hour long video footage of a busy city marketplace.

History

Event

International Symposium on Visual Computing (6th : 2010 : Las Vegas, Nevada)

Pagination

89 - 98

Publisher

Springer

Location

Las Vegas, Nevada

Place of publication

Berlin, Germany

Start date

2010-11-29

End date

2010-12-01

ISBN-13

9783642172762

ISBN-10

3642172768

Language

eng

Publication classification

E1.1 Full written paper - refereed

Title of proceedings

ISVC 2010 : Advances in Visual Computing : Proceedings of the 6th international symposium on visual computing 2010

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC