• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>EUSIPCO 2007;European signal processing conference >TRACKING MOVING OBJECTS IN VIDEO USING ENHANCED MEAN SHIFT ANDREGION-BASED MOTION FIELD
【24h】

TRACKING MOVING OBJECTS IN VIDEO USING ENHANCED MEAN SHIFT ANDREGION-BASED MOTION FIELD

机译：使用增强的均值漂移和基于区域的运动场跟踪视频中的运动对象

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 scheme for moving object trackingrnfrom videos by combining mean shift and motion fieldrnstatistics. For mean shift, we employ an enhanced spatialrangernmean shift that enables a reduced number of oversegmentation.rnFor motion statistics, we combine the opticalrnflow and high-order moment to generate motion regions thatrnare associated with moving objects (or object parts). Experimentsrnhave been conducted on several indoor and outdoorrn(color/gray-scale) image sequences ranging from simplernto median complexity. To evaluate the performance, threernobjective criteria are applied in addition to the visual inspection.rnThe results show that the proposed method is promisingrnfor moving object tracking in video, with an averaging detectionrnrate of 95%. Further, the proposed scheme is comparedrnwith that using the conventional mean shift for the tracking,rnindicating a significantly reduction in false alarm ( ≈ 30%).
机译：在本文中，我们提出了一种通过结合均值漂移和运动场统计来从视频跟踪运动对象的方案。对于均值平移，我们采用增强的空间范围均值平移，以减少过度分割的次数。对于运动统计，我们将光流和高阶矩结合起来生成与运动物体（或物体部分）相关的运动区域。已经对从简单到中值复杂度的几个室内和室外（彩色/灰度）图像序列进行了实验。为了评估性能，除了视觉检查外，还应用了三个客观标准。结果表明，该方法对视频中的运动目标跟踪具有广阔的前景，平均检测率为95％。此外，将所提出的方案与使用传统的均值漂移进行跟踪的方案进行了比较，表明虚假警报的显着减少（≈30％）。

著录项

  • 来源
  • 会议地点 Poznan(PL);Poznan(PL)
  • 作者

    Tiesheng Wang; rnIrene Y.H. Gu; rnMats Viberg; rnZhongping Cao; rnNuan Song;

  • 作者单位

    Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, China tieshengw@sjtu.edu.cn;

    rnDepartment of Signals and Systems, Chalmers University of Technology, Sweden irenegu@chalmers.se;

    rnDepartment of Signals and Systems, Chalmers University of Technology, Sweden viberg@chalmers.se;

    rnDepartment of Signals and Systems, Chalmers University of Technology, Sweden;

    rnDepartment of Signals and Systems, Chalmers University of Technology, Sweden;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 通信理论;
  • 关键词

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