Document Detail


Visual Tracking with Online Multiple Instance Learning.
MedLine Citation:
PMID:  21173445     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
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 further 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.
Authors:
Boris Babenko; Ming-Hsuan Yang; Serge Belongie
Related Documents :
1852555 - Preadolescent religious experience enhances temporal lobe signs in normal young adults.
12480635 - Differences in clinical experiences based on gender of third-year medical students in a...
19586145 - Winning and positive affect can lead to reckless gambling.
10188265 - Further cross-cultural validation of the theory of mental self-government.
11840735 - Quality management in neuropathology.
15669415 - The effects of behavioral skills training on staff implementation of discrete-trial tea...
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2010-12-14
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  -     ISSN:  1939-3539     ISO Abbreviation:  -     Publication Date:  2010 Dec 
Date Detail:
Created Date:  2010-12-21     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Affiliation:
University of California, San Diego, San Diego.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  On Kleinberg's Stochastic Discrimination Procedure.
Next Document:  Fingerprint Indexing Based on Minutia Cylinder-Code.