.png){kind=icon}
返回
CNN tracking based on data augmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2020.105594.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Correlation filter based tracking methods have aroused increasing attention due to the appealing performance on tracking benchmark datasets. For each frame, a filter is trained to separate the object from its background. Considering that the object always undergoes challenging situations, the trained filter should consider both external and internal distractions. In this paper, we propose a data augmentation based robust visual tracking algorithm to better generalize the training data. Specifically, data augmentation technique is utilized to generate training samples to improve the robustness of the training filter. Then hierarchical convolutional neural network (CNN) features are utilized to encode the target and the augmented sample. Different from previous work, we exploit to use a hash matrix to reduce the dimension of the CNN features. Next, the correlation filter tracking method is employed. The tracking results of multiple hash features are combined to locate the target. Extensive experiments on five large scale datasets show that the proposed method achieves comparable results to state-of-the-art trackers. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Visual tracking
Data augmentation
Convolutional neural network
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容