Enhancement of background subtraction techniques using a second derivative in gradient direction filter

Farah Yasmin Abdul Rahman, Aini Hussain, Wan Mimi Diyana Wan Zaki, Halimah Badioze Zaman, Nooritawati Md Tahir

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A new approach was proposed to improve traditional background subtraction (BGS) techniques by integrating a gradient-based edge detector called a second derivative in gradient direction (SDGD) filter with the BGS output. The four fundamental BGS techniques, namely, frame difference (FD), approximate median (AM), running average (RA), and running Gaussian average (RGA), showed imperfect foreground pixels generated specifically at the boundary. The pixel intensity was lesser than the preset threshold value, and the blob size was smaller. The SDGD filter was introduced to enhance edge detection upon the completion of each basic BGS technique as well as to complement the missing pixels. The results proved that fusing the SDGD filter with each elementary BGS increased segmentation performance and suited postrecording video applications. Evidently, the analysis using F-score and average accuracy percentage proved this, and, as such, it can be concluded that this new hybrid BGS technique improved upon existing techniques.

Original languageEnglish
Article number598708
JournalJournal of Electrical and Computer Engineering
DOIs
Publication statusPublished - 2013

Fingerprint

Pixels
Derivatives
Edge detection
Detectors

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Computer Science(all)

Cite this

@article{491deb4143db43b992e5317d98568d41,
title = "Enhancement of background subtraction techniques using a second derivative in gradient direction filter",
abstract = "A new approach was proposed to improve traditional background subtraction (BGS) techniques by integrating a gradient-based edge detector called a second derivative in gradient direction (SDGD) filter with the BGS output. The four fundamental BGS techniques, namely, frame difference (FD), approximate median (AM), running average (RA), and running Gaussian average (RGA), showed imperfect foreground pixels generated specifically at the boundary. The pixel intensity was lesser than the preset threshold value, and the blob size was smaller. The SDGD filter was introduced to enhance edge detection upon the completion of each basic BGS technique as well as to complement the missing pixels. The results proved that fusing the SDGD filter with each elementary BGS increased segmentation performance and suited postrecording video applications. Evidently, the analysis using F-score and average accuracy percentage proved this, and, as such, it can be concluded that this new hybrid BGS technique improved upon existing techniques.",
author = "{Abdul Rahman}, {Farah Yasmin} and Aini Hussain and {Wan Zaki}, {Wan Mimi Diyana} and {Badioze Zaman}, Halimah and {Md Tahir}, Nooritawati",
year = "2013",
doi = "10.1155/2013/598708",
language = "English",
journal = "Journal of Electrical and Computer Engineering",
issn = "2090-0147",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Enhancement of background subtraction techniques using a second derivative in gradient direction filter

AU - Abdul Rahman, Farah Yasmin

AU - Hussain, Aini

AU - Wan Zaki, Wan Mimi Diyana

AU - Badioze Zaman, Halimah

AU - Md Tahir, Nooritawati

PY - 2013

Y1 - 2013

N2 - A new approach was proposed to improve traditional background subtraction (BGS) techniques by integrating a gradient-based edge detector called a second derivative in gradient direction (SDGD) filter with the BGS output. The four fundamental BGS techniques, namely, frame difference (FD), approximate median (AM), running average (RA), and running Gaussian average (RGA), showed imperfect foreground pixels generated specifically at the boundary. The pixel intensity was lesser than the preset threshold value, and the blob size was smaller. The SDGD filter was introduced to enhance edge detection upon the completion of each basic BGS technique as well as to complement the missing pixels. The results proved that fusing the SDGD filter with each elementary BGS increased segmentation performance and suited postrecording video applications. Evidently, the analysis using F-score and average accuracy percentage proved this, and, as such, it can be concluded that this new hybrid BGS technique improved upon existing techniques.

AB - A new approach was proposed to improve traditional background subtraction (BGS) techniques by integrating a gradient-based edge detector called a second derivative in gradient direction (SDGD) filter with the BGS output. The four fundamental BGS techniques, namely, frame difference (FD), approximate median (AM), running average (RA), and running Gaussian average (RGA), showed imperfect foreground pixels generated specifically at the boundary. The pixel intensity was lesser than the preset threshold value, and the blob size was smaller. The SDGD filter was introduced to enhance edge detection upon the completion of each basic BGS technique as well as to complement the missing pixels. The results proved that fusing the SDGD filter with each elementary BGS increased segmentation performance and suited postrecording video applications. Evidently, the analysis using F-score and average accuracy percentage proved this, and, as such, it can be concluded that this new hybrid BGS technique improved upon existing techniques.

UR - http://www.scopus.com/inward/record.url?scp=84890105629&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890105629&partnerID=8YFLogxK

U2 - 10.1155/2013/598708

DO - 10.1155/2013/598708

M3 - Article

AN - SCOPUS:84890105629

JO - Journal of Electrical and Computer Engineering

JF - Journal of Electrical and Computer Engineering

SN - 2090-0147

M1 - 598708

ER -