Background segmentation with feedback: The pixel-based adaptive segmenter

Martin Hofmann, Philipp Tiefenbacher, Gerhard Rigoll

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

565 Scopus citations

Abstract

In this paper we present a novel method for foreground segmentation. Our proposed approach follows a non-parametric background modeling paradigm, thus the background is modeled by a history of recently observed pixel values. The foreground decision depends on a decision threshold. The background update is based on a learning parameter. We extend both of these parameters to dynamic per-pixel state variables and introduce dynamic controllers for each of them. Furthermore, both controllers are steered by an estimate of the background dynamics. In our experiments, the proposed Pixel-Based Adaptive Segmenter (PBAS) outperforms most state-of-the-art methods.

Original languageEnglish
Title of host publication2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012
Pages38-43
Number of pages6
DOIs
StatePublished - 2012
Event2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012 - Providence, RI, United States
Duration: 16 Jun 201221 Jun 2012

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012
Country/TerritoryUnited States
CityProvidence, RI
Period16/06/1221/06/12

Fingerprint

Dive into the research topics of 'Background segmentation with feedback: The pixel-based adaptive segmenter'. Together they form a unique fingerprint.

Cite this