Ieee Transactions on Pattern Analysis and Machine Intelligence High-speed Tracking with Kernelized Correlation Filters
Ieee Transactions on Pattern Analysis and Machine Intelligence High-speed Tracking with Kernelized Correlation Filters
复制标题
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
中科院分区：
文献类型：
--
作者：
João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
大多数现代跟踪器的核心组件是一个判别式分类器，其任务是区分目标和周围环境。为了应对自然图像的变化，该分类器通常使用平移和缩放的样本块进行训练。这类样本集充满了冗余——任何重叠的像素都被约束为相同的。基于这一简单的观察，我们针对数千个平移样本块的数据集提出了一个分析模型。通过证明所得的数据矩阵是循环矩阵，我们可以使用离散傅里叶变换将其对角化，从而将存储量和计算量降低几个数量级。有趣的是，对于线性回归，我们的公式等同于一种相关滤波器，一些速度最快的竞争跟踪器使用了这种滤波器。然而，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，它与它的线性对应算法具有完全相同的复杂度。在此基础上，我们还通过一个线性核提出了线性相关滤波器的一种快速多通道扩展，我们称之为对偶相关滤波器（DCF）。在一个50个视频的基准测试中，KCF和DCF都优于排名靠前的跟踪器，如Struck或TLD，尽管它们每秒能处理数百帧，并且只用几行代码实现（算法1）。为了鼓励进一步的发展，我们的跟踪框架已开源。
—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.