Fast background subtraction algorithm using two-level sampling and silhouette detection

Dae Youn Lee, Jae Kyun Ahn, Chang-Su Kim

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

10 Citations (Scopus)

Abstract

An efficient background subtraction algorithm using two-level sampling and silhouette detection is proposed in this work. In the two-level sampling, we identify moving objects at the block level and then at the pixel level. Then, in the silhouette detection, around each sampled foreground pixel, we refine the shapes of foreground objects. We also develop two fast modes for the silhouette detection, which utilizes the spatio-temporal coherence of moving foreground objects. Simulation results demonstrate that the proposed algorithm provides accurate segmentation results without flickering artifacts, while requiring a low computational load.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages3177-3180
Number of pages4
DOIs
Publication statusPublished - 2009 Dec 1
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: 2009 Nov 72009 Nov 12

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period09/11/709/11/12

Fingerprint

Pixels
Flickering
Sampling

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Lee, D. Y., Ahn, J. K., & Kim, C-S. (2009). Fast background subtraction algorithm using two-level sampling and silhouette detection. In Proceedings - International Conference on Image Processing, ICIP (pp. 3177-3180). [5414397] https://doi.org/10.1109/ICIP.2009.5414397

Fast background subtraction algorithm using two-level sampling and silhouette detection. / Lee, Dae Youn; Ahn, Jae Kyun; Kim, Chang-Su.

Proceedings - International Conference on Image Processing, ICIP. 2009. p. 3177-3180 5414397.

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

Lee, DY, Ahn, JK & Kim, C-S 2009, Fast background subtraction algorithm using two-level sampling and silhouette detection. in Proceedings - International Conference on Image Processing, ICIP., 5414397, pp. 3177-3180, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 09/11/7. https://doi.org/10.1109/ICIP.2009.5414397
Lee DY, Ahn JK, Kim C-S. Fast background subtraction algorithm using two-level sampling and silhouette detection. In Proceedings - International Conference on Image Processing, ICIP. 2009. p. 3177-3180. 5414397 https://doi.org/10.1109/ICIP.2009.5414397
Lee, Dae Youn ; Ahn, Jae Kyun ; Kim, Chang-Su. / Fast background subtraction algorithm using two-level sampling and silhouette detection. Proceedings - International Conference on Image Processing, ICIP. 2009. pp. 3177-3180
@inproceedings{b08142ffac6f4bb5a095cdbdcacfb42d,
title = "Fast background subtraction algorithm using two-level sampling and silhouette detection",
abstract = "An efficient background subtraction algorithm using two-level sampling and silhouette detection is proposed in this work. In the two-level sampling, we identify moving objects at the block level and then at the pixel level. Then, in the silhouette detection, around each sampled foreground pixel, we refine the shapes of foreground objects. We also develop two fast modes for the silhouette detection, which utilizes the spatio-temporal coherence of moving foreground objects. Simulation results demonstrate that the proposed algorithm provides accurate segmentation results without flickering artifacts, while requiring a low computational load.",
author = "Lee, {Dae Youn} and Ahn, {Jae Kyun} and Chang-Su Kim",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ICIP.2009.5414397",
language = "English",
isbn = "9781424456543",
pages = "3177--3180",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Fast background subtraction algorithm using two-level sampling and silhouette detection

AU - Lee, Dae Youn

AU - Ahn, Jae Kyun

AU - Kim, Chang-Su

PY - 2009/12/1

Y1 - 2009/12/1

N2 - An efficient background subtraction algorithm using two-level sampling and silhouette detection is proposed in this work. In the two-level sampling, we identify moving objects at the block level and then at the pixel level. Then, in the silhouette detection, around each sampled foreground pixel, we refine the shapes of foreground objects. We also develop two fast modes for the silhouette detection, which utilizes the spatio-temporal coherence of moving foreground objects. Simulation results demonstrate that the proposed algorithm provides accurate segmentation results without flickering artifacts, while requiring a low computational load.

AB - An efficient background subtraction algorithm using two-level sampling and silhouette detection is proposed in this work. In the two-level sampling, we identify moving objects at the block level and then at the pixel level. Then, in the silhouette detection, around each sampled foreground pixel, we refine the shapes of foreground objects. We also develop two fast modes for the silhouette detection, which utilizes the spatio-temporal coherence of moving foreground objects. Simulation results demonstrate that the proposed algorithm provides accurate segmentation results without flickering artifacts, while requiring a low computational load.

UR - http://www.scopus.com/inward/record.url?scp=77951969969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951969969&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5414397

DO - 10.1109/ICIP.2009.5414397

M3 - Conference contribution

AN - SCOPUS:77951969969

SN - 9781424456543

SP - 3177

EP - 3180

BT - Proceedings - International Conference on Image Processing, ICIP

ER -