跳到主要导航 跳到搜索 跳到主要内容

A new trajectory clustering algorithm using temporal smoothness for motion segmentation

  • F. Shi
  • , Z. Zhou*
  • , J. Xiao
  • , W. Wu
  • *此作品的通讯作者
  • Beihang University
  • CAS - Ningbo Institute of Material Technology and Engineering

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this paper, a new trajectory clustering algorithm for motion segmentation is proposed. Our key contribution is to use temporal smoothness constraint to facilitate segmentation of incomplete trajectories, which leads to high robustness to missing data. We further show that most motions in foreground of a scene can be approximately represented by a set of translational motion models. Based on this assumption, a new clustering strategy is proposed to separate foreground objects from background. Finally, a series of experiments show that our approach is more effective and outperforms several state-of-the-art methods.

源语言英语
主期刊名2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
出版商IEEE Computer Society
4044-4048
页数5
ISBN(印刷版)9781479923410
DOI
出版状态已出版 - 2013
活动2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, 澳大利亚
期限: 15 9月 201318 9月 2013

出版系列

姓名2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

会议

会议2013 20th IEEE International Conference on Image Processing, ICIP 2013
国家/地区澳大利亚
Melbourne, VIC
时期15/09/1318/09/13

指纹

探究 'A new trajectory clustering algorithm using temporal smoothness for motion segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此