Background subtraction using spatio-temporal continuities

Srenivas Varadarajan, Lina Karam, Dinei Florencio

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

4 Citations (Scopus)

Abstract

This paper presents a novel scheme for dynamically recovering a background image from consecutive frames of a video sequence based on spatial and temporal continuities. The proposed background subtraction algorithm applies a boundary-level spatial continuity constraint in order to detect and correct ghosting, which corresponds to incorrectly classified foreground regions due to fast moving objects. A pixel-level spatial continuity metric that effectively recovers regions with partial ghosting problems is also proposed in this paper together with a selective application of a temporal continuity metric in order to prevent strong pixel transitions in the background from hindering the background recovery process. The proposed method can also be applied successfully to sequences with deformable foreground objects and non-uniform motion. Simulation results show that the extracted background, when used for foreground detection, results in a higher performance in terms of recall and precision as compared to existing popular schemes.

Original languageEnglish (US)
Title of host publication2010 2nd European Workshop on Visual Information Processing, EUVIP2010
Pages144-148
Number of pages5
DOIs
StatePublished - 2010
Event2nd European Workshop on Visual Information Processing, EUVIP2010 - Paris, France
Duration: Jul 5 2010Jul 7 2010

Other

Other2nd European Workshop on Visual Information Processing, EUVIP2010
CountryFrance
CityParis
Period7/5/107/7/10

Fingerprint

Pixels
Recovery

Keywords

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

ASJC Scopus subject areas

  • Information Systems

Cite this

Varadarajan, S., Karam, L., & Florencio, D. (2010). Background subtraction using spatio-temporal continuities. In 2010 2nd European Workshop on Visual Information Processing, EUVIP2010 (pp. 144-148). [5699142] https://doi.org/10.1109/EUVIP.2010.5699142

Background subtraction using spatio-temporal continuities. / Varadarajan, Srenivas; Karam, Lina; Florencio, Dinei.

2010 2nd European Workshop on Visual Information Processing, EUVIP2010. 2010. p. 144-148 5699142.

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

Varadarajan, S, Karam, L & Florencio, D 2010, Background subtraction using spatio-temporal continuities. in 2010 2nd European Workshop on Visual Information Processing, EUVIP2010., 5699142, pp. 144-148, 2nd European Workshop on Visual Information Processing, EUVIP2010, Paris, France, 7/5/10. https://doi.org/10.1109/EUVIP.2010.5699142
Varadarajan S, Karam L, Florencio D. Background subtraction using spatio-temporal continuities. In 2010 2nd European Workshop on Visual Information Processing, EUVIP2010. 2010. p. 144-148. 5699142 https://doi.org/10.1109/EUVIP.2010.5699142
Varadarajan, Srenivas ; Karam, Lina ; Florencio, Dinei. / Background subtraction using spatio-temporal continuities. 2010 2nd European Workshop on Visual Information Processing, EUVIP2010. 2010. pp. 144-148
@inproceedings{f2cf165eba3445f085fa182e8df57f2f,
title = "Background subtraction using spatio-temporal continuities",
abstract = "This paper presents a novel scheme for dynamically recovering a background image from consecutive frames of a video sequence based on spatial and temporal continuities. The proposed background subtraction algorithm applies a boundary-level spatial continuity constraint in order to detect and correct ghosting, which corresponds to incorrectly classified foreground regions due to fast moving objects. A pixel-level spatial continuity metric that effectively recovers regions with partial ghosting problems is also proposed in this paper together with a selective application of a temporal continuity metric in order to prevent strong pixel transitions in the background from hindering the background recovery process. The proposed method can also be applied successfully to sequences with deformable foreground objects and non-uniform motion. Simulation results show that the extracted background, when used for foreground detection, results in a higher performance in terms of recall and precision as compared to existing popular schemes.",
keywords = "Background extraction, Motion, Object removal, Occlusion removal, Video",
author = "Srenivas Varadarajan and Lina Karam and Dinei Florencio",
year = "2010",
doi = "10.1109/EUVIP.2010.5699142",
language = "English (US)",
isbn = "9781424472871",
pages = "144--148",
booktitle = "2010 2nd European Workshop on Visual Information Processing, EUVIP2010",

}

TY - GEN

T1 - Background subtraction using spatio-temporal continuities

AU - Varadarajan, Srenivas

AU - Karam, Lina

AU - Florencio, Dinei

PY - 2010

Y1 - 2010

N2 - This paper presents a novel scheme for dynamically recovering a background image from consecutive frames of a video sequence based on spatial and temporal continuities. The proposed background subtraction algorithm applies a boundary-level spatial continuity constraint in order to detect and correct ghosting, which corresponds to incorrectly classified foreground regions due to fast moving objects. A pixel-level spatial continuity metric that effectively recovers regions with partial ghosting problems is also proposed in this paper together with a selective application of a temporal continuity metric in order to prevent strong pixel transitions in the background from hindering the background recovery process. The proposed method can also be applied successfully to sequences with deformable foreground objects and non-uniform motion. Simulation results show that the extracted background, when used for foreground detection, results in a higher performance in terms of recall and precision as compared to existing popular schemes.

AB - This paper presents a novel scheme for dynamically recovering a background image from consecutive frames of a video sequence based on spatial and temporal continuities. The proposed background subtraction algorithm applies a boundary-level spatial continuity constraint in order to detect and correct ghosting, which corresponds to incorrectly classified foreground regions due to fast moving objects. A pixel-level spatial continuity metric that effectively recovers regions with partial ghosting problems is also proposed in this paper together with a selective application of a temporal continuity metric in order to prevent strong pixel transitions in the background from hindering the background recovery process. The proposed method can also be applied successfully to sequences with deformable foreground objects and non-uniform motion. Simulation results show that the extracted background, when used for foreground detection, results in a higher performance in terms of recall and precision as compared to existing popular schemes.

KW - Background extraction

KW - Motion

KW - Object removal

KW - Occlusion removal

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=79951619400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951619400&partnerID=8YFLogxK

U2 - 10.1109/EUVIP.2010.5699142

DO - 10.1109/EUVIP.2010.5699142

M3 - Conference contribution

AN - SCOPUS:79951619400

SN - 9781424472871

SP - 144

EP - 148

BT - 2010 2nd European Workshop on Visual Information Processing, EUVIP2010

ER -