IEEE Trans Pattern Anal Mach Intell. 2015 Mar;37(3):583-96. doi: 10.1109/TPAMI.2014.2345390.
The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with translated and scaled sample patches. Such sets of samples are riddled with redundancies-any overlapping pixels are constrained to be the same. Based on this simple observation, we propose an analytic model for datasets of thousands of translated patches. By showing that the resulting data matrix is circulant, we can diagonalize it with the discrete Fourier transform, reducing both storage and computation by several orders of magnitude. Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers. For kernel regression, however, we derive a new kernelized correlation filter (KCF), that unlike other kernel algorithms has the exact same complexity as its linear counterpart. Building on it, we also propose a fast multi-channel extension of linear correlation filters, via a linear kernel, which we call dual correlation filter (DCF). Both KCF and DCF outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite running at hundreds of frames-per-second, and being implemented in a few lines of code (Algorithm 1). To encourage further developments, our tracking framework was made open-source.
大多数现代跟踪器的核心组件是一个判别分类器，其任务是区分目标和周围环境。为了应对自然图像变化，该分类器通常使用经过翻译和缩放的样本补丁进行训练。这种样本集充满了冗余 - 任何重叠的像素都必须相同。基于这一简单的观察，我们为数千个翻译补丁数据集提出了一个分析模型。通过表明得到的数据矩阵是循环的，我们可以用离散傅里叶变换对其进行对角化，从而将存储和计算减少几个数量级。有趣的是，对于线性回归，我们的公式等效于一些最快的竞争跟踪器使用的相关滤波器。但是对于核回归，我们推导出了一种新的核化相关滤波器（KCF），与其他核算法不同，它与线性对应物具有完全相同的复杂度。在此基础上，我们还通过线性核提出了一种快速的线性相关滤波器的多通道扩展，我们称之为对偶相关滤波器（DCF）。KCF 和 DCF 在 50 个视频基准测试中都优于排名靠前的跟踪器，如 Struck 或 TLD，尽管它们以每秒数百帧的速度运行，并且仅用几行代码（算法 1）实现。为了鼓励进一步的发展，我们的跟踪框架被开源。
