Correlation filter-based visual tracking via adaptive weighted CNN features fusion
Correlation filter-based visual tracking via adaptive weighted CNN features fusion
复制标题
DOI：
10.1049/iet-ipr.2017.0443
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Zhaohui Hao;Guixi Liu;Haoyang Zhang
中科院分区：
文献类型：
--
作者：
Zhaohui Hao;Guixi Liu;Haoyang Zhang
视觉目标跟踪是计算机视觉中的一项重要而富有挑战性的任务。在这项研究中，作者提出了一种新的视觉跟踪方法，将跟踪任务分解为平移和尺度估计。在平移估计中，他们采用了多个具有层次卷积神经网络（cnn）特征的自适应相关滤波器来更准确地估计目标位置。为了充分利用来自不同CNN层的多层次特征，他们提出了一种自适应加权算法来融合相关响应图。在尺度估计中，采用具有定向梯度直方图特征的一维相关滤波器来估计尺度变化。在50个具有挑战性的基准视频序列上的大量实验结果表明，该算法优于最先进的算法。
Visual object tracking is an important and challenging task in computer vision. In this study, the authors propose a novel visual tracking approach by decomposing the tracking task into translation and scale estimation. In translation estimation, they employ multiple adaptive correlation filters with features of hierarchical convolutional neural networks (CNNs) to more accurately estimate the target location. To make full use of multi-level features from different CNN layers, they propose an adaptive weighted algorithm to fuse correlation response maps. In scale estimation, a one-dimensional correlation filter with histogram of oriented gradient (HOG) features is employed to estimate the scale variation. Extensive experimental results on 50 challenging benchmark video sequences demonstrate that the proposed algorithm outperforms state-of-the-art algorithms.