Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Support Vector Tracking Shai Avidan
 

Summary: Support Vector Tracking
Shai Avidan
MobilEye Vision Technologies,
24 Mishol Hadkalim,
Jerusalem, Israel,
E-mail: avidan@mobileye.com
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 classi-
fication score. To account for large motions between succes-
sive 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.
1 Introduction
Tracking algorithms find how does an image region move
from one frame to the next. This implies the existence of an
error function to be minimized, such as the sum of squared

  

Source: Avidan, Shai - School of Computer Science, Interdisciplinary Center, Herzliya Israel

 

Collections: Computer Technologies and Information Sciences