Fast Object Segmentation in Unconstrained Video

A. Papazoglou, V. Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a technique for separating foreground objects from the background in a video. Our method is fast, fully automatic, and makes minimal assumptions about the video. This enables handling essentially unconstrained settings, including rapidly moving background, arbitrary object motion and appearance, and non-rigid deformations and articulations. In experiments on two datasets containing over 1400 video shots, our method outperforms a state-of-the-art background subtraction technique [4] as well as methods based on clustering point tracks [6, 18, 19]. Moreover, it performs comparably to recent video object segmentation methods based on object proposals [14, 16, 27], while being orders of magnitude faster.
Original languageEnglish
Title of host publicationComputer Vision (ICCV), 2013 IEEE International Conference on
Pages1777-1784
Number of pages8
DOIs
Publication statusPublished - 1 Dec 2013

Keywords

  • image motion analysis
  • image segmentation
  • object recognition
  • video signal processing
  • background subtraction technique
  • clustering point
  • fast object segmentation
  • foreground object separation
  • nonrigid deformation
  • object motion analysis
  • unconstrained video
  • video object segmentation
  • video shot
  • Adaptive optics
  • Estimation
  • Labeling
  • Motion segmentation
  • Object segmentation
  • Optical imaging
  • Optical variables measurement
  • video
  • video segmentation

Fingerprint Dive into the research topics of 'Fast Object Segmentation in Unconstrained Video'. Together they form a unique fingerprint.

Cite this