Background recovery from video sequences using motion parameters

Srenivas Varadarajan, Lina Karam, Dinei Florencio

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

6 Citations (Scopus)

Abstract

This paper presents a novel scheme for extracting a still background occluded by a number of foreground objects, moving in different directions and velocities in a video sequence, such that every background pixel is exposed in at least one of the frames. Each identified foreground object is decomposed into blocks. The proposed scheme is able to efficiently estimate, for each foreground block, a source frame from which the occluded background pixels can be extracted. The pixels of the identified source frames are used to populate the co-located occluded pixels in the initial frame. The efficacy and the simplicity of the algorithm lie in its capacity to recover the background directly from the estimated source frames instead of performing a foreground-background classification for every frame. The proposed algorithm is robust to variations in lighting and is effective in removing both rigid and deformable foreground objects. Simulation results are presented to illustrate the performance of the proposed scheme.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages989-992
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China
Duration: Apr 19 2009Apr 24 2009

Other

Other2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
CountryTaiwan, Province of China
CityTaipei
Period4/19/094/24/09

Fingerprint

Pixels
Recovery
Lighting

Keywords

  • Background extraction
  • Motion
  • Object removal
  • Occlusion removal
  • Video

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Varadarajan, S., Karam, L., & Florencio, D. (2009). Background recovery from video sequences using motion parameters. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 989-992). [4959752] https://doi.org/10.1109/ICASSP.2009.4959752

Background recovery from video sequences using motion parameters. / Varadarajan, Srenivas; Karam, Lina; Florencio, Dinei.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 989-992 4959752.

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

Varadarajan, S, Karam, L & Florencio, D 2009, Background recovery from video sequences using motion parameters. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4959752, pp. 989-992, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, Taiwan, Province of China, 4/19/09. https://doi.org/10.1109/ICASSP.2009.4959752
Varadarajan S, Karam L, Florencio D. Background recovery from video sequences using motion parameters. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 989-992. 4959752 https://doi.org/10.1109/ICASSP.2009.4959752
Varadarajan, Srenivas ; Karam, Lina ; Florencio, Dinei. / Background recovery from video sequences using motion parameters. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. pp. 989-992
@inproceedings{4ea9124e41bb40348e3e57bacabba842,
title = "Background recovery from video sequences using motion parameters",
abstract = "This paper presents a novel scheme for extracting a still background occluded by a number of foreground objects, moving in different directions and velocities in a video sequence, such that every background pixel is exposed in at least one of the frames. Each identified foreground object is decomposed into blocks. The proposed scheme is able to efficiently estimate, for each foreground block, a source frame from which the occluded background pixels can be extracted. The pixels of the identified source frames are used to populate the co-located occluded pixels in the initial frame. The efficacy and the simplicity of the algorithm lie in its capacity to recover the background directly from the estimated source frames instead of performing a foreground-background classification for every frame. The proposed algorithm is robust to variations in lighting and is effective in removing both rigid and deformable foreground objects. Simulation results are presented to illustrate the performance of the proposed scheme.",
keywords = "Background extraction, Motion, Object removal, Occlusion removal, Video",
author = "Srenivas Varadarajan and Lina Karam and Dinei Florencio",
year = "2009",
doi = "10.1109/ICASSP.2009.4959752",
language = "English (US)",
isbn = "9781424423545",
pages = "989--992",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Background recovery from video sequences using motion parameters

AU - Varadarajan, Srenivas

AU - Karam, Lina

AU - Florencio, Dinei

PY - 2009

Y1 - 2009

N2 - This paper presents a novel scheme for extracting a still background occluded by a number of foreground objects, moving in different directions and velocities in a video sequence, such that every background pixel is exposed in at least one of the frames. Each identified foreground object is decomposed into blocks. The proposed scheme is able to efficiently estimate, for each foreground block, a source frame from which the occluded background pixels can be extracted. The pixels of the identified source frames are used to populate the co-located occluded pixels in the initial frame. The efficacy and the simplicity of the algorithm lie in its capacity to recover the background directly from the estimated source frames instead of performing a foreground-background classification for every frame. The proposed algorithm is robust to variations in lighting and is effective in removing both rigid and deformable foreground objects. Simulation results are presented to illustrate the performance of the proposed scheme.

AB - This paper presents a novel scheme for extracting a still background occluded by a number of foreground objects, moving in different directions and velocities in a video sequence, such that every background pixel is exposed in at least one of the frames. Each identified foreground object is decomposed into blocks. The proposed scheme is able to efficiently estimate, for each foreground block, a source frame from which the occluded background pixels can be extracted. The pixels of the identified source frames are used to populate the co-located occluded pixels in the initial frame. The efficacy and the simplicity of the algorithm lie in its capacity to recover the background directly from the estimated source frames instead of performing a foreground-background classification for every frame. The proposed algorithm is robust to variations in lighting and is effective in removing both rigid and deformable foreground objects. Simulation results are presented to illustrate the performance of the proposed scheme.

KW - Background extraction

KW - Motion

KW - Object removal

KW - Occlusion removal

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=70349214959&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349214959&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2009.4959752

DO - 10.1109/ICASSP.2009.4959752

M3 - Conference contribution

AN - SCOPUS:70349214959

SN - 9781424423545

SP - 989

EP - 992

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -