Deformable Parts Correlation Filters for Robust Visual Tracking
Deformable Parts Correlation Filters for Robust Visual Tracking
复制标题
DOI：
10.1109/tcyb.2017.2716101
复制
发表时间：
2016-05
影响因子：
11.8
通讯作者：
A. Lukežič;Luka Čehovin Zajc;M. Kristan
中科院分区：
文献类型：
--
作者：
A. Lukežič;Luka Čehovin Zajc;M. Kristan
可变形部件模型通过主要解决非刚性物体变形和自遮挡在跟踪方面显示出巨大的潜力，但根据最近的基准测试，它们往往落后于整体方法。原因是必须估计潜在的大量的自由度来进行目标定位，并且通常假设星座拓扑的简化使推理易于处理。我们提出了一种新的星座模型公式，该模型使用相关滤波器处理单个凸代价函数中的几何和视觉约束，并推导出一个高效的优化，以最大限度地提高全连通星座的后检推理。我们提出了一种跟踪器，它在两个细节层次上对目标进行建模。粗层对应一个根相关滤波器和一个用于近似目标定位的新颜色模型，而中层表示由新的可变形相关滤波器星座组成，用于细化目标定位。结果跟踪器在极具挑战性的OTB、VOT2014和VOT2015基准测试中进行了严格分析，显示出最先进的性能和实时运行。
Deformable parts models show a great potential in tracking by principally addressing nonrigid object deformations and self occlusions, but according to recent benchmarks, they often lag behind the holistic approaches. The reason is that potentially large number of degrees of freedom have to be estimated for object localization and simplifications of the constellation topology are often assumed to make the inference tractable. We present a new formulation of the constellation model with correlation filters that treats the geometric and visual constraints within a single convex cost function and derive a highly efficient optimization for maximum a posteriori inference of a fully connected constellation. We propose a tracker that models the object at two levels of detail. The coarse level corresponds a root correlation filter and a novel color model for approximate object localization, while the mid-level representation is composed of the new deformable constellation of correlation filters that refine the object location. The resulting tracker is rigorously analyzed on a highly challenging OTB, VOT2014, and VOT2015 benchmarks, exhibits a state-of-the-art performance and runs in real-time.