Robust Object Tracking with Online Multiple Instance Learning

TLDR

Tracking by detection methods have recently shown promising real‑time performance. The paper proposes a novel online MIL algorithm to robustly track an object from its first‑frame location without additional information, aiming to outperform traditional supervised methods. The algorithm trains an online discriminative classifier via Multiple Instance Learning, bootstrapping positive and negative samples from the current tracker state to mitigate drift caused by labeling errors. Experiments on challenging video clips demonstrate the proposed MIL tracker’s superior performance and real‑time capability.

Abstract

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.