Visual tracking with online multiple instance learning
Research output: Contribution to journal › Conference article › Research › peer-review
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.
Original language | English |
---|---|
Journal | 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 |
Pages (from-to) | 983-990 |
Number of pages | 8 |
DOIs | |
Publication status | Published - 2009 |
Externally published | Yes |
Event | 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States Duration: 20 Jun 2009 → 25 Jun 2009 |
Conference
Conference | 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 |
---|---|
Country | United States |
City | Miami, FL |
Period | 20/06/2009 → 25/06/2009 |
ID: 302050162