Target Response Adaptation for Correlation Filter Tracking

Handle URI:
http://hdl.handle.net/10754/622156
Title:
Target Response Adaptation for Correlation Filter Tracking
Authors:
Bibi, Adel Aamer ( 0000-0002-6169-3918 ) ; Mueller, Matthias; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
Most correlation filter (CF) based trackers utilize the circulant structure of the training data to learn a linear filter that best regresses this data to a hand-crafted target response. These circularly shifted patches are only approximations to actual translations in the image, which become unreliable in many realistic tracking scenarios including fast motion, occlusion, etc. In these cases, the traditional use of a single centered Gaussian as the target response impedes tracker performance and can lead to unrecoverable drift. To circumvent this major drawback, we propose a generic framework that can adaptively change the target response from frame to frame, so that the tracker is less sensitive to the cases where circular shifts do not reliably approximate translations. To do that, we reformulate the underlying optimization to solve for both the filter and target response jointly, where the latter is regularized by measurements made using actual translations. This joint problem has a closed form solution and thus allows for multiple templates, kernels, and multi-dimensional features. Extensive experiments on the popular OTB100 benchmark show that our target adaptive framework can be combined with many CF trackers to realize significant overall performance improvement (ranging from 3 %-13.5% in precision and 3.2 %-13% in accuracy), especially in categories where this adaptation is necessary (e.g. fast motion, motion blur, etc.). © Springer International Publishing AG 2016.
KAUST Department:
King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
Citation:
Bibi A, Mueller M, Ghanem B (2016) Target Response Adaptation for Correlation Filter Tracking. Lecture Notes in Computer Science: 419–433. Available: http://dx.doi.org/10.1007/978-3-319-46466-4_25.
Publisher:
Springer Nature
Journal:
Lecture Notes in Computer Science
Issue Date:
16-Sep-2016
DOI:
10.1007/978-3-319-46466-4_25
Type:
Book Chapter
ISSN:
0302-9743; 1611-3349
Sponsors:
This research work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-319-46466-4_25
Appears in Collections:
Book Chapters

Full metadata record

DC FieldValue Language
dc.contributor.authorBibi, Adel Aameren
dc.contributor.authorMueller, Matthiasen
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2017-01-02T08:10:22Z-
dc.date.available2017-01-02T08:10:22Z-
dc.date.issued2016-09-16en
dc.identifier.citationBibi A, Mueller M, Ghanem B (2016) Target Response Adaptation for Correlation Filter Tracking. Lecture Notes in Computer Science: 419–433. Available: http://dx.doi.org/10.1007/978-3-319-46466-4_25.en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.doi10.1007/978-3-319-46466-4_25en
dc.identifier.urihttp://hdl.handle.net/10754/622156-
dc.description.abstractMost correlation filter (CF) based trackers utilize the circulant structure of the training data to learn a linear filter that best regresses this data to a hand-crafted target response. These circularly shifted patches are only approximations to actual translations in the image, which become unreliable in many realistic tracking scenarios including fast motion, occlusion, etc. In these cases, the traditional use of a single centered Gaussian as the target response impedes tracker performance and can lead to unrecoverable drift. To circumvent this major drawback, we propose a generic framework that can adaptively change the target response from frame to frame, so that the tracker is less sensitive to the cases where circular shifts do not reliably approximate translations. To do that, we reformulate the underlying optimization to solve for both the filter and target response jointly, where the latter is regularized by measurements made using actual translations. This joint problem has a closed form solution and thus allows for multiple templates, kernels, and multi-dimensional features. Extensive experiments on the popular OTB100 benchmark show that our target adaptive framework can be combined with many CF trackers to realize significant overall performance improvement (ranging from 3 %-13.5% in precision and 3.2 %-13% in accuracy), especially in categories where this adaptation is necessary (e.g. fast motion, motion blur, etc.). © Springer International Publishing AG 2016.en
dc.description.sponsorshipThis research work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-46466-4_25en
dc.subjectAdaptive target designen
dc.subjectCorrelation filter trackingen
dc.titleTarget Response Adaptation for Correlation Filter Trackingen
dc.typeBook Chapteren
dc.contributor.departmentKing Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabiaen
dc.identifier.journalLecture Notes in Computer Scienceen
kaust.authorBibi, Adel Aameren
kaust.authorMueller, Matthiasen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.