A Bayesian approach to video object segmentation via merging 3-D watershed volumes

Yu Pao Tsai*, Chih Chuan Lai, Yi Ping Hung, Zen-Chung Shih

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

24 Scopus citations

Abstract

In this letter, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of three-dimensional (3-D) watershed volumes, where each watershed volume is a series of corresponding two-dimensional (2-D) image regions. These 2-D image regions are obtained by applying to each image frame the marker-controlled watershed segmentation, where the markers are extracted by first generating a set of initial markers via temporal tracking and then refining the markers with two shrinking schemes: the iterative adaptive erosion and the verification against a presimplified watershed segmentation. Next, in the second stage, we use a Markov random field to model the spatio-temporal relationship among the 3-D watershed volumes that are obtained from the first stage. Then, the desired video objects can be extracted by merging watershed volumes having similar motion characteristics within a Bayesian framework. A major advantage of this method is that it can take into account the global motion information contained in each watershed volume. Our experiments have shown that the proposed method has potential for extracting moving objects from a video sequence.

Original languageEnglish
Pages (from-to)175-180
Number of pages6
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume15
Issue number1
DOIs
StatePublished - 1 Jan 2005

Keywords

  • Markov random field
  • Three-dimensional (3-D) watershed volume
  • Video object segmentation
  • Watershed segmentation

Fingerprint Dive into the research topics of 'A Bayesian approach to video object segmentation via merging 3-D watershed volumes'. Together they form a unique fingerprint.

Cite this