期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 33, 期 8, 页码 1619-1632出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2010.226
关键词
Visual Tracking; multiple instance learning; online boosting
资金
- US National Science Foundation (NSF) [0448615]
- NSF [DGE-0333451]
- US Office of Naval Research Grant [N00014-08-1-0638]
- University of California
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [0448615] Funding Source: National Science Foundation
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据