• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >A Biologically Inspired Appearance Model for Robust Visual Tracking
【24h】

A Biologically Inspired Appearance Model for Robust Visual Tracking

机译：基于生物学启发的外观模型，可实现强大的视觉跟踪

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

In this paper, we propose a biologically inspired appearance model for robust visual tracking. Motivated in part by the success of the hierarchical organization of the primary visual cortex (area V1), we establish an architecture consisting of five layers: whitening, rectification, normalization, coding, and pooling. The first three layers stem from the models developed for object recognition. In this paper, our attention focuses on the coding and pooling layers. In particular, we use a discriminative sparse coding method in the coding layer along with spatial pyramid representation in the pooling layer, which makes it easier to distinguish the target to be tracked from its background in the presence of appearance variations. An extensive experimental study shows that the proposed method has higher tracking accuracy than several state-of-the-art trackers.
机译：在本文中，我们提出了一种生物学启发的外观模型，用于强大的视觉跟踪。主要是由于主要视觉皮层（区域V1）的分层组织的成功，我们建立了一个由五层组成的体系结构：美白，矫正，归一化，编码和合并。前三层源自为对象识别而开发的模型。在本文中，我们的注意力集中在编码和池化层。特别是，我们在编码层中使用了判别式稀疏编码方法，在池化层中使用了空间金字塔表示法，这使得在出现外观变化的情况下，更容易从背景中区分出要跟踪的目标。广泛的实验研究表明，与几种最新的跟踪器相比，该方法具有更高的跟踪精度。

著录项

  • 来源
  • 作者

    Shengping Zhang; Xiangyuan Lan; Hongxun Yao; Huiyu Zhou; Dacheng Tao; Xuelong Li;

  • 作者单位

    School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China;

    Department of Computer Science, Hong Kong Baptist University, Hong Kong;

    School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China;

    School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast, U.K.;

    Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology, University of Technology, Sydney, 81 Broadway Street, Ultimo, NSW, Australia;

    Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an, Shaanxi, China;

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

    Visualization; Biological system modeling; Encoding; Object recognition; Brain modeling; Robustness;

    机译：可视化;生物系统建模;编码;目标识别;脑部建模;鲁棒性;

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