Skip to main navigation Skip to search Skip to main content

Auto-generated strokes for motion segmentation

  • Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

We propose a new approach to motion segmentation that is based on auto-generated strokes. The novelty of the approach is twofold. First, inspired by recent work of other researchers we formulate the problem as that of interactive segmentation. Instead of inputting the strokes by the user, the strokes in our approach are auto-generated. The second novelty of the paper is formulation in which, unlike in many other motion segmentation algorithms, we do not use complex algorithm which fuses the output of multiple cues to segment foreground objects, a simple and effective maximum hybrid similarity method is presented. The maximum hybrid similarity does not need to set the threshold in advance. Experimental results have shown the superiority of the proposed method in extracting moving objects.

Original languageEnglish
Title of host publication2011 IEEE International Symposium of Circuits and Systems, ISCAS 2011
Pages857-860
Number of pages4
DOIs
StatePublished - 2011
Event2011 IEEE International Symposium of Circuits and Systems, ISCAS 2011 - Rio de Janeiro, Brazil
Duration: 15 May 2011 → 18 May 2011

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
ISSN (Print)0271-4310

Conference

Conference2011 IEEE International Symposium of Circuits and Systems, ISCAS 2011
Country/TerritoryBrazil
CityRio de Janeiro
Period15/05/11 → 18/05/11

Fingerprint

Dive into the research topics of 'Auto-generated strokes for motion segmentation'. Together they form a unique fingerprint.

Cite this