...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Knowledge-Based Systems >Deep convolutional neural networks for thermal infrared object tracking
【24h】

Deep convolutional neural networks for thermal infrared object tracking

机译：用于热红外目标跟踪的深度卷积神经网络

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Unlike the visual object tracking, thermal infrared object tracking can track a target object in total darkness. Therefore, it has broad applications, such as in rescue and video surveillance at night. However, there are few studies in this field mainly because thermal infrared images have several unwanted attributes, which make it difficult to obtain the discriminative features of the target. Considering the powerful representational ability of convolutional neural networks and their successful application in visual tracking, we transfer the pre-trained convolutional neural networks based on visible images to thermal infrared tracking. We observe that the features from the fully-connected layer are not suitable for thermal infrared tracking due to the lack of spatial information of the target, while the features from the convolution layers are. Besides, the features from a single convolution layer are not robust to various challenges. Based on this observation, we propose a correlation filter based ensemble tracker with multi-layer convolutional features for thermal infrared tracking (MCFTS). Firstly, we use pre-trained convolutional neural networks to extract the features of the multiple convolution layers of the thermal infrared target. Then, a correlation filter is used to construct multiple weak trackers with the corresponding convolution layer features. These weak trackers give the response maps of the target's location. Finally, we propose an ensemble method that coalesces these response maps to get a stronger one. Furthermore, a simple but effective scale estimation strategy is exploited to boost the tracking accuracy. To evaluate the performance of the proposed tracker, we carry out experiments on two thermal infrared tracking benchmarks: VOT-TIR 2015 and VOT-TIR 2016. The experimental results demonstrate that our tracker is effective and achieves promising performance. (C) 2017 Elsevier B.V. All rights reserved.
机译：与视觉对象跟踪不同，热红外对象跟踪可以在完全黑暗的情况下跟踪目标对象。因此，它具有广泛的应用，例如在夜间的救援和视频监视中。但是，该领域的研究很少，主要是因为红外热图像具有一些不需要的属性，这使得难以获得目标的辨别特征。考虑到卷积神经网络的强大表示能力及其在视觉跟踪中的成功应用，我们将基于可见图像的预训练卷积神经网络转换为热红外跟踪。我们观察到，由于缺乏目标的空间信息，来自全连接层的特征不适合用于热红外跟踪，而来自卷积层的特征却不适合。此外，来自单个卷积层的特征对于各种挑战都不可靠。基于此观察，我们提出了一种基于相关滤波器的集成跟踪器，该跟踪器具有用于热红外跟踪（MCFTS）的多层卷积特征。首先，我们使用预训练的卷积神经网络来提取热红外目标的多个卷积层的特征。然后，使用相关滤波器构造具有相应卷积层特征的多个弱跟踪器。这些弱的跟踪器会给出目标位置的响应图。最后，我们提出一种集合方法，将这些响应图合并以得到更强大的方法。此外，利用一种简单但有效的比例估计策略来提高跟踪精度。为了评估建议的跟踪器的性能，我们在两个热红外跟踪基准上进行了实验：VOT-TIR 2015和VOT-TIR2016。实验结果表明，我们的跟踪器是有效的，并取得了令人鼓舞的性能。 （C）2017 Elsevier B.V.保留所有权利。

著录项

  • 来源
    《Knowledge-Based Systems》 |2017年第15期|189-198|共10页
  • 作者

    Liu Qiao; Lu Xiaohuan; He Zhenyu; Zhang Chunkai; Chen Wen-Sheng;

  • 作者单位

    Harbin Inst Technol, Sch Comp Sci & Technol, Shenzhen Grad Sch, Harbin, Heilongjiang, Peoples R China;

    Harbin Inst Technol, Sch Comp Sci & Technol, Shenzhen Grad Sch, Harbin, Heilongjiang, Peoples R China;

    Harbin Inst Technol, Sch Comp Sci & Technol, Shenzhen Grad Sch, Harbin, Heilongjiang, Peoples R China;

    Harbin Inst Technol, Sch Comp Sci & Technol, Shenzhen Grad Sch, Harbin, Heilongjiang, Peoples R China;

    Shenzhen Univ, Coll Math & Stat, Shenzhen Key Lab Media Secur, Shenzhen, Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Thermal infrared tracking; Convolutional features; Correlation filter; Ensemble method;

    机译：热红外跟踪;卷积特征;相关滤波器;集合法;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号