Dynamosaicing: Mosaicing of dynamic scenes

Alex Rav-Acha*, Yael Pritch, Dani Lischinski, Shmuel Peleg

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

52 Scopus citations

Abstract

This paper explores the manipulation of time in video editing, enabling to control the chronological time of events. These time manipulations include slowing down (or postponing) some dynamic events while speeding up (or advancing) others. When a video camera scans a scene, aligning all the events to a single time interval will result in a panoramic movie. Time manipulations are obtained by first constructing an aligned space-time volume from the input video, and then sweeping a continuous 2D slice (time front) through that volume, generating a new sequence of images. For dynamic scenes, aligning the input video frames poses an important challenge. We propose to align dynamic scenes using a new notion of "dynamics constancy", which is more appropriate for this task than the traditional assumption of "brightness constancy". Another challenge is to avoid visual seams inside moving objects and other visual artifacts resulting from sweeping the space-time volumes with time fronts of arbitrary geometry. To avoid such artifacts, we formulate the problem of finding optimal time front geometry as one of finding a minimal cut in a 4D graph, and solve it using max-flow methods.

Original languageEnglish
Pages (from-to)1789-1801
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume29
Issue number10
DOIs
StatePublished - 2007

Bibliographical note

Funding Information:
This research was supported (in part) by the EU through contract IST-2001-39184 BENOGO, and by a grant from the Israel Science Foundation.

Keywords

  • Dynamic scene
  • Graph cuts
  • Panoramic mosaicing
  • Space-time volume
  • Time manipulations
  • Video editing
  • Video mosaicing

Fingerprint

Dive into the research topics of 'Dynamosaicing: Mosaicing of dynamic scenes'. Together they form a unique fingerprint.

Cite this