Robust object tracking with online multiple instance learning

Boris Babenko, Ming Hsuan Yang, Serge Belongie

Research output: Contribution to journalArticle

1711 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

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Robust object tracking with online multiple instance learning'. Together they form a unique fingerprint.

  • Cite this