Dependent Motion Segmentation in Moving Camera Videos: A Survey

Dependent Motion Segmentation in Moving Camera Videos: A Survey
复制标题

移动摄像机视频中的相关运动分割:一项调查

DOI:
10.1109/access.2018.2872733
复制
发表时间:
2018-10
期刊:
影响因子:
3.9
通讯作者:
Shuai Chang
Shuai Chang
中科院分区:
计算机科学3区
文献类型:
--
作者:
Cuicui Zhang;Zhilei Liu;Chongke Bi;Shuai Chang

文献摘要

参考文献

相似文献

运动分割在各种计算机视觉和模式识别应用中起着核心作用。在运动摄像机视频中,摄像机运动引起的动态背景和多个运动目标引起的目标运动相互混合、相互依赖,使得摄像机运动和目标运动的分割非常困难。这是已知的相关运动分割。虽然在静态场景中的运动分割是一个相对容易的工作,在动态场景中的相关运动分割是非常具有挑战性的,由于高度的混合和依赖之间的相机运动和对象的运动。最近,大量的作品已经开发的任务相关的运动分割。然而,它们的表现仍然远远落后于人类的感知。本文研究、分析和回顾了最重要的、最近开发的相关运动分割技术,并提出了一种分类策略,根据这些技术的特点和特征将其分为不同的组。此外,我们还讨论了各种技术的优缺点,并提出了进一步研究的方向。
Motion segmentation plays a central role in a variety of computer vision and pattern recognition applications. In moving camera videos, the dynamic background caused by camera motion and the object motions caused by multiple moving objects are mixed and dependent with each other making the segmentation of camera motion and object motions quite difficult. This is the known dependent motion segmentation. Although motion segmentation in static scenes is a relative easy work, the dependent motion segmentation in dynamic scenes is very challenging due to the high mixture and dependence between camera motion and object motions. Recently, a large number of works have been developed for the task of dependent motion segmentation. However, their performances are still far behind human perceptions. In this paper, we studied, analyzed, and reviewed the most important and recent developed dependent motion segmentation techniques and proposed a classification strategy to categorize these techniques into different groups according to their characteristics and features. Furthermore, we also discussed the advantages and disadvantages of each kind of techniques and provided suggestions for further research directions.
DOI: 10.1007/978-3-642-33786-4_30
发表时间: 2012-10
期刊: --
影响因子: --
作者:
Quanyi Mo;B. Draper
通讯作者: Quanyi Mo;B. Draper
DOI: 10.1109/icra.2014.6907299
发表时间: 2014-05
期刊: 2014 IEEE International Conference on Robotics and Automation (ICRA)
影响因子: --
作者:
Tsung-Han Lin;C. Wang
通讯作者: Tsung-Han Lin;C. Wang
DOI: 10.1109/iranianmvip.2011.6121592
发表时间: 2011-11
期刊: 2011 7th Iranian Conference on Machine Vision and Image Processing
影响因子: --
作者:
Nima Forouzanfar;H. Ebrahimnezhad;A. Ebrahimi
通讯作者: Nima Forouzanfar;H. Ebrahimnezhad;A. Ebrahimi
DOI: 10.1109/cvpr.2014.54
发表时间: 2014-06
期刊: 2014 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Adeel Mumtaz;Weichen Zhang;Antoni B. Chan
通讯作者: Adeel Mumtaz;Weichen Zhang;Antoni B. Chan
通过基于图的流形排序进行鲁棒的交互式图像分割
DOI: 10.1007/s41095-015-0024-2
发表时间: 2015-09
影响因子: 6.9
作者:
Hong Li;Wen Wu;Enhua Wu
通讯作者: Enhua Wu