Improving Global Multi-target Tracking with Local Updates

Research output: Research - peer-reviewArticle in proceeding

Abstract

We propose a scheme to explicitly detect and resolve ambiguous situations in multiple target tracking. During periods of uncertainty, our method applies multiple local single target trackers to hypothesise short term tracks. These tracks are combined with the tracks obtained by a global multi-target tracker, if they result in a reduction in the global cost function. Since tracking failures typically arise when targets become occluded, we propose a local data association scheme to maintain the target identities in these situations. We demonstrate a reduction of up to 50% in the global cost function, which in turn leads to superior per- formance on several challenging benchmark sequences. Additionally, we show tracking results in sports videos where poor video quality and fre- quent and severe occlusions between multiple players pose difficulties for state-of-the-art trackers.
Close

Details

We propose a scheme to explicitly detect and resolve ambiguous situations in multiple target tracking. During periods of uncertainty, our method applies multiple local single target trackers to hypothesise short term tracks. These tracks are combined with the tracks obtained by a global multi-target tracker, if they result in a reduction in the global cost function. Since tracking failures typically arise when targets become occluded, we propose a local data association scheme to maintain the target identities in these situations. We demonstrate a reduction of up to 50% in the global cost function, which in turn leads to superior per- formance on several challenging benchmark sequences. Additionally, we show tracking results in sports videos where poor video quality and fre- quent and severe occlusions between multiple players pose difficulties for state-of-the-art trackers.
Original languageEnglish
Title of host publicationComputer Vision - ECCV 2014 Workshops : Zurich, Switzerland, September 6-7 and 12, 2014, Proceedings, Part III
EditorsLourdes Agapito, Michael M. Bronstein, Carsten Rother
Number of pages17
PublisherSpringer
Publication date2015
Edition3
Pages174-190
ISBN (Print)978-3-319-16198-3
ISBN (Electronic)978-3-319-16199-0
DOI
StatePublished - 2015
Publication categoryResearch
Peer-reviewedYes
EventECCV Workshop - Zürich, Switzerland
Duration: 12 Sep 2014 → …

Workshop

WorkshopECCV Workshop
LandSwitzerland
ByZürich
Periode12/09/2014 → …
SeriesLecture Notes in Computer Science
Number8927
ISSN0302-9743

Download statistics

No data available
ID: 212438066