Robust object tracking with online multiple instance learning

Boris Babenko, Ming Hsuan Yang, Serge Belongie

Research output: Contribution to journalArticle

1614 Citations (Scopus)

Abstract

In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called tracking by detection has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.

Original languageEnglish
Article number5674053
Pages (from-to)1619-1632
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Volume33
Issue number8
DOIs
Publication statusPublished - 2011 Jun 10

Fingerprint

Object Tracking
Classifiers
Classifier
Real-time
Supervised learning
Supervised Learning
Bootstrap
Learning algorithms
Learning Algorithm
Experimental Results
Learning
Object

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

@article{9fbc1ed3df344ffea4f9fcff0f35f4d2,
title = "Robust object tracking with online multiple instance learning",
abstract = "In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called tracking by detection has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.",
author = "Boris Babenko and Yang, {Ming Hsuan} and Serge Belongie",
year = "2011",
month = "6",
day = "10",
doi = "10.1109/TPAMI.2010.226",
language = "English",
volume = "33",
pages = "1619--1632",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "8",

}

Robust object tracking with online multiple instance learning. / Babenko, Boris; Yang, Ming Hsuan; Belongie, Serge.

In: IEEE transactions on pattern analysis and machine intelligence, Vol. 33, No. 8, 5674053, 10.06.2011, p. 1619-1632.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust object tracking with online multiple instance learning

AU - Babenko, Boris

AU - Yang, Ming Hsuan

AU - Belongie, Serge

PY - 2011/6/10

Y1 - 2011/6/10

N2 - In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called tracking by detection has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.

AB - In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called tracking by detection has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.

UR - http://www.scopus.com/inward/record.url?scp=79959527478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959527478&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2010.226

DO - 10.1109/TPAMI.2010.226

M3 - Article

AN - SCOPUS:79959527478

VL - 33

SP - 1619

EP - 1632

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 8

M1 - 5674053

ER -