Object movements synopsis viapart assembling and stitching

Yongwei Nie, Hanqiu Sun, Ping Li, Chunxia Xiao, Kwan-Liu Ma

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Video synopsis aims at removing video's less important information, while preserving its key content for fast browsing, retrieving, or efficient storing. Previous video synopsis methods, including frame-based and object-based approaches that remove valueless whole frames or combine objects from time shots, cannot handle videos with redundancies existing in the movements of video object. In this paper, we present a novel part-based object movements synopsis method, which can effectively compress the redundant information of a moving video object and represent the synopsized object seamlessly. Our method works by part-based assembling and stitching. The object movement sequence is first divided into several part movement sequences. Then, we optimally assemble moving parts from different part sequences together to produce an initial synopsis result. The optimal assembling is formulated as a part movement assignment problem on a Markov Random Field (MRF), which guarantees the most important moving parts are selected while preserving both the spatial compatibility between assembled parts and the chronological order of parts. Finally, we present a non-linear spatiotemporal optimization formulation to stitch the assembled parts seamlessly, and achieve the final compact video object synopsis. The experiments on a variety of input video objects have demonstrated the effectiveness of the presented synopsis method.

Original languageEnglish (US)
Article number6702519
Pages (from-to)1303-1315
Number of pages13
JournalIEEE Transactions on Visualization and Computer Graphics
Volume20
Issue number9
DOIs
StatePublished - Jan 1 2014

Fingerprint

Redundancy
Experiments

Keywords

  • belief propagation
  • MRF optimization
  • part assembling
  • part stitching
  • Video synopsis

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

Object movements synopsis viapart assembling and stitching. / Nie, Yongwei; Sun, Hanqiu; Li, Ping; Xiao, Chunxia; Ma, Kwan-Liu.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 20, No. 9, 6702519, 01.01.2014, p. 1303-1315.

Research output: Contribution to journalArticle

Nie, Yongwei ; Sun, Hanqiu ; Li, Ping ; Xiao, Chunxia ; Ma, Kwan-Liu. / Object movements synopsis viapart assembling and stitching. In: IEEE Transactions on Visualization and Computer Graphics. 2014 ; Vol. 20, No. 9. pp. 1303-1315.
@article{d5995ee0fe3748cbaa2770104055e258,
title = "Object movements synopsis viapart assembling and stitching",
abstract = "Video synopsis aims at removing video's less important information, while preserving its key content for fast browsing, retrieving, or efficient storing. Previous video synopsis methods, including frame-based and object-based approaches that remove valueless whole frames or combine objects from time shots, cannot handle videos with redundancies existing in the movements of video object. In this paper, we present a novel part-based object movements synopsis method, which can effectively compress the redundant information of a moving video object and represent the synopsized object seamlessly. Our method works by part-based assembling and stitching. The object movement sequence is first divided into several part movement sequences. Then, we optimally assemble moving parts from different part sequences together to produce an initial synopsis result. The optimal assembling is formulated as a part movement assignment problem on a Markov Random Field (MRF), which guarantees the most important moving parts are selected while preserving both the spatial compatibility between assembled parts and the chronological order of parts. Finally, we present a non-linear spatiotemporal optimization formulation to stitch the assembled parts seamlessly, and achieve the final compact video object synopsis. The experiments on a variety of input video objects have demonstrated the effectiveness of the presented synopsis method.",
keywords = "belief propagation, MRF optimization, part assembling, part stitching, Video synopsis",
author = "Yongwei Nie and Hanqiu Sun and Ping Li and Chunxia Xiao and Kwan-Liu Ma",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/TVCG.2013.2297931",
language = "English (US)",
volume = "20",
pages = "1303--1315",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "9",

}

TY - JOUR

T1 - Object movements synopsis viapart assembling and stitching

AU - Nie, Yongwei

AU - Sun, Hanqiu

AU - Li, Ping

AU - Xiao, Chunxia

AU - Ma, Kwan-Liu

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Video synopsis aims at removing video's less important information, while preserving its key content for fast browsing, retrieving, or efficient storing. Previous video synopsis methods, including frame-based and object-based approaches that remove valueless whole frames or combine objects from time shots, cannot handle videos with redundancies existing in the movements of video object. In this paper, we present a novel part-based object movements synopsis method, which can effectively compress the redundant information of a moving video object and represent the synopsized object seamlessly. Our method works by part-based assembling and stitching. The object movement sequence is first divided into several part movement sequences. Then, we optimally assemble moving parts from different part sequences together to produce an initial synopsis result. The optimal assembling is formulated as a part movement assignment problem on a Markov Random Field (MRF), which guarantees the most important moving parts are selected while preserving both the spatial compatibility between assembled parts and the chronological order of parts. Finally, we present a non-linear spatiotemporal optimization formulation to stitch the assembled parts seamlessly, and achieve the final compact video object synopsis. The experiments on a variety of input video objects have demonstrated the effectiveness of the presented synopsis method.

AB - Video synopsis aims at removing video's less important information, while preserving its key content for fast browsing, retrieving, or efficient storing. Previous video synopsis methods, including frame-based and object-based approaches that remove valueless whole frames or combine objects from time shots, cannot handle videos with redundancies existing in the movements of video object. In this paper, we present a novel part-based object movements synopsis method, which can effectively compress the redundant information of a moving video object and represent the synopsized object seamlessly. Our method works by part-based assembling and stitching. The object movement sequence is first divided into several part movement sequences. Then, we optimally assemble moving parts from different part sequences together to produce an initial synopsis result. The optimal assembling is formulated as a part movement assignment problem on a Markov Random Field (MRF), which guarantees the most important moving parts are selected while preserving both the spatial compatibility between assembled parts and the chronological order of parts. Finally, we present a non-linear spatiotemporal optimization formulation to stitch the assembled parts seamlessly, and achieve the final compact video object synopsis. The experiments on a variety of input video objects have demonstrated the effectiveness of the presented synopsis method.

KW - belief propagation

KW - MRF optimization

KW - part assembling

KW - part stitching

KW - Video synopsis

UR - http://www.scopus.com/inward/record.url?scp=84905241270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905241270&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2013.2297931

DO - 10.1109/TVCG.2013.2297931

M3 - Article

AN - SCOPUS:84905241270

VL - 20

SP - 1303

EP - 1315

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 9

M1 - 6702519

ER -