TY - GEN

T1 - Visual tracking with online multiple instance learning

AU - Babenko, Boris

AU - Belongie, Serge

AU - Yang, Ming Hsuan

PY - 2009

Y1 - 2009

N2 - In this paper, we address the problem of learning an adaptive appearance model for object tracking. In particular, a class of tracking techniques called "tracking by detection" have been shown to give promising results at realtime 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 degrades 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 present a novel online MIL algorithm for object tracking that achieves superior results with real-time performance.

AB - In this paper, we address the problem of learning an adaptive appearance model for object tracking. In particular, a class of tracking techniques called "tracking by detection" have been shown to give promising results at realtime 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 degrades 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 present a novel online MIL algorithm for object tracking that achieves superior results with real-time performance.

UR - http://www.scopus.com/inward/record.url?scp=70450188146&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2009.5206737

DO - 10.1109/CVPRW.2009.5206737

M3 - Conference article

AN - SCOPUS:70450188146

SP - 983

EP - 990

JO - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

JF - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

T2 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Y2 - 20 June 2009 through 25 June 2009

ER -