Colour co-occurrence and edge based background modelling with conditional random field shadow removal

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

1 Citation (Scopus)

Abstract

Good foreground detection is important as the basis to many other video processing algorithms. Current approaches are able produce accurate detection but under tight conditions and constraints. Thus, we have developed an algorithm that proved to be robust to shadow and afterimage noise, colour similarity between foreground and background and slight movements of the moving foreground. Our approach to weaken the constraints is by fusing gradientbased background modelling, a colour co-occurrence based approach, and a 3D conditional random field shadow and afterimage removal. Our results show improvement over existing algorithms in terms of robustness and accuracy. Our method is suitable to be implemented alongside other video processing techniques such as people counting, face recognition, etc.

Original languageEnglish
Title of host publicationProceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
Pages137-141
Number of pages5
Volume4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010 - Chengdu
Duration: 9 Jul 201011 Jul 2010

Other

Other2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
CityChengdu
Period9/7/1011/7/10

Fingerprint

Color
Processing
Face recognition

Keywords

  • Background modelling
  • Gradient image
  • Hypothesis testing
  • Random jield
  • Shadow removal

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Zulkifley, M. A., & Moran, B. (2010). Colour co-occurrence and edge based background modelling with conditional random field shadow removal. In Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010 (Vol. 4, pp. 137-141). [5564863] https://doi.org/10.1109/ICCSIT.2010.5564863

Colour co-occurrence and edge based background modelling with conditional random field shadow removal. / Zulkifley, Mohd Asyraf; Moran, Bill.

Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010. Vol. 4 2010. p. 137-141 5564863.

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

Zulkifley, MA & Moran, B 2010, Colour co-occurrence and edge based background modelling with conditional random field shadow removal. in Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010. vol. 4, 5564863, pp. 137-141, 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010, Chengdu, 9/7/10. https://doi.org/10.1109/ICCSIT.2010.5564863
Zulkifley MA, Moran B. Colour co-occurrence and edge based background modelling with conditional random field shadow removal. In Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010. Vol. 4. 2010. p. 137-141. 5564863 https://doi.org/10.1109/ICCSIT.2010.5564863
Zulkifley, Mohd Asyraf ; Moran, Bill. / Colour co-occurrence and edge based background modelling with conditional random field shadow removal. Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010. Vol. 4 2010. pp. 137-141
@inproceedings{453e743b8a214201bafee9ab5ecfc4c6,
title = "Colour co-occurrence and edge based background modelling with conditional random field shadow removal",
abstract = "Good foreground detection is important as the basis to many other video processing algorithms. Current approaches are able produce accurate detection but under tight conditions and constraints. Thus, we have developed an algorithm that proved to be robust to shadow and afterimage noise, colour similarity between foreground and background and slight movements of the moving foreground. Our approach to weaken the constraints is by fusing gradientbased background modelling, a colour co-occurrence based approach, and a 3D conditional random field shadow and afterimage removal. Our results show improvement over existing algorithms in terms of robustness and accuracy. Our method is suitable to be implemented alongside other video processing techniques such as people counting, face recognition, etc.",
keywords = "Background modelling, Gradient image, Hypothesis testing, Random jield, Shadow removal",
author = "Zulkifley, {Mohd Asyraf} and Bill Moran",
year = "2010",
doi = "10.1109/ICCSIT.2010.5564863",
language = "English",
isbn = "9781424455386",
volume = "4",
pages = "137--141",
booktitle = "Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010",

}

TY - GEN

T1 - Colour co-occurrence and edge based background modelling with conditional random field shadow removal

AU - Zulkifley, Mohd Asyraf

AU - Moran, Bill

PY - 2010

Y1 - 2010

N2 - Good foreground detection is important as the basis to many other video processing algorithms. Current approaches are able produce accurate detection but under tight conditions and constraints. Thus, we have developed an algorithm that proved to be robust to shadow and afterimage noise, colour similarity between foreground and background and slight movements of the moving foreground. Our approach to weaken the constraints is by fusing gradientbased background modelling, a colour co-occurrence based approach, and a 3D conditional random field shadow and afterimage removal. Our results show improvement over existing algorithms in terms of robustness and accuracy. Our method is suitable to be implemented alongside other video processing techniques such as people counting, face recognition, etc.

AB - Good foreground detection is important as the basis to many other video processing algorithms. Current approaches are able produce accurate detection but under tight conditions and constraints. Thus, we have developed an algorithm that proved to be robust to shadow and afterimage noise, colour similarity between foreground and background and slight movements of the moving foreground. Our approach to weaken the constraints is by fusing gradientbased background modelling, a colour co-occurrence based approach, and a 3D conditional random field shadow and afterimage removal. Our results show improvement over existing algorithms in terms of robustness and accuracy. Our method is suitable to be implemented alongside other video processing techniques such as people counting, face recognition, etc.

KW - Background modelling

KW - Gradient image

KW - Hypothesis testing

KW - Random jield

KW - Shadow removal

UR - http://www.scopus.com/inward/record.url?scp=77958538960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77958538960&partnerID=8YFLogxK

U2 - 10.1109/ICCSIT.2010.5564863

DO - 10.1109/ICCSIT.2010.5564863

M3 - Conference contribution

SN - 9781424455386

VL - 4

SP - 137

EP - 141

BT - Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010

ER -