Robust Object Tracking with Online Multiple Instance Learning

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 33; no. 8; pp. 1619 - 1632
Main Authors: Babenko, B., Ming-Hsuan Yang, Belongie, S.
Format: Journal Article
Language:English
Published: Los Alamitos, CA IEEE 01.08.2011
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Adaptation model
Agriculture
Algorithmics. Computability. Computer arithmetics
Algorithms
Applied sciences
Artificial intelligence
Boosting
Classifiers
Computer science; control theory; systems
Data processing. List processing. Character string processing
Exact sciences and technology
Frames
Learning
Memory organisation. Data processing
multiple instance learning
On-line systems
Online
online boosting
Pattern recognition. Digital image processing. Computational geometry
Real time
Software
Studies
Target tracking
Theoretical computing
Tracking
Training
Trains
Visual Tracking
Computer vision
Discriminant analysis
Data analysis
Target tracking
On line
Tracking
Motion estimation
Image processing
Video signal
Visual Tracking
Real time
Aggregate model
Bootstrapping
Supervised learning
Remolded sample
Classification
multiple instance learning
online boosting
Bootstrap
Localization
ISSN:0162-8828, 1939-3539, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
ISSN:0162-8828
1939-3539
1939-3539
DOI:10.1109/TPAMI.2010.226