Support vector tracking

Shai Avidan

Support vector tracking

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

Abstract

Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.

Original language	English
Pages (from-to)	I184-I191
Journal	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	1
State	Published - 2001
Externally published	Yes
Event	2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI, United States Duration: 8 Dec 2001 → 14 Dec 2001

Cite this

@article{475751de7d5c441da58d973cc5fbf081,

title = "Support vector tracking",

abstract = "Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.",

author = "Shai Avidan",

year = "2001",

language = "אנגלית",

volume = "1",

pages = "I184--I191",

journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

issn = "1063-6919",

publisher = "IEEE Computer Society",

note = "null ; Conference date: 08-12-2001 Through 14-12-2001",

}

TY - JOUR

T1 - Support vector tracking

AU - Avidan, Shai

PY - 2001

Y1 - 2001

N2 - Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.

AB - Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.

UR - http://www.scopus.com/inward/record.url?scp=0035683738&partnerID=8YFLogxK

M3 - מאמר מכנס

AN - SCOPUS:0035683738

VL - 1

SP - I184-I191

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

Y2 - 8 December 2001 through 14 December 2001

ER -

Support vector tracking

Abstract

Other files and links

Fingerprint

Cite this