Struck: Structured Output Tracking with Kernels

TLDR

Adaptive tracking‑by‑detection methods are common in computer vision, yet they rely on converting estimated positions into training examples and treat classification and tracking objectives separately, leaving the best approach unclear. This paper introduces a framework for adaptive visual object tracking that uses structured output prediction. The method employs a kernelised structured output SVM learned online, eliminates the intermediate classification step, incorporates a budgeting scheme to limit support vectors, and is implemented on the GPU for high‑frame‑rate operation. Experiments show the tracker outperforms state‑of‑the‑art methods on benchmark videos and that adding features or kernels further boosts performance.

Abstract

Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction) is not explicitly coupled to the objective for the tracker (estimation of object position). In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. By explicitly allowing the output space to express the needs of the tracker, we avoid the need for an intermediate classification step. Our method uses a kernelised structured output support vector machine (SVM), which is learned online to provide adaptive tracking. To allow our tracker to run at high frame rates, we (a) introduce a budgeting mechanism that prevents the unbounded growth in the number of support vectors that would otherwise occur during tracking, and (b) show how to implement tracking on the GPU. Experimentally, we show that our algorithm is able to outperform state-of-the-art trackers on various benchmark videos. Additionally, we show that we can easily incorporate additional features and kernels into our framework, which results in increased tracking performance.