High-Speed Tracking with Kernelized Correlation Filters
High-Speed Tracking with Kernelized Correlation Filters
复制标题
DOI：
10.1109/tpami.2014.2345390
复制
发表时间：
2015-03-01
影响因子：
23.6
通讯作者：
Batista, Jorge
中科院分区：
文献类型：
--
作者：
Henriques, Joao F.;Caseiro, Rui;Batista, Jorge
大多数现代跟踪器的核心组件是判别分类器，其任务是区分目标和周围环境。为了科普自然图像变化，该分类器通常使用平移和缩放的样本块进行训练。这样的样本集充满了冗余任何重叠的像素都被限制为相同的。基于这个简单的观察，我们提出了一个分析模型的数据集的数千个翻译补丁。通过证明结果数据矩阵是循环的，我们可以用离散傅里叶变换将其对角化，从而将存储和计算量减少几个数量级。有趣的是，对于线性回归，我们的公式相当于一个相关滤波器，被一些最快的竞争对手所使用。然而，对于核回归，我们推导出一种新的核相关滤波器（KCF），与其他核算法不同，它具有与线性算法完全相同的复杂性。在此基础上，我们还提出了一个快速的多通道线性相关滤波器的扩展，通过一个线性内核，我们称之为双相关滤波器（DCF）。KCF和DCF在50个视频基准测试中的表现都超过了顶级跟踪器，如Struck或Strike，尽管它们以每秒数百帧的速度运行，并且只需要几行代码（算法1）。为了鼓励进一步的发展，我们的跟踪框架是开源的。
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.