Low-complexity background subtraction based on spatial similarity

Sangwook Lee, Chul Hee Lee

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Robust detection of moving objects from video sequences is an important task in machine vision systems and applications. To detect moving objects, accurate background subtraction is essential. In real environments, due to complex and various background types, background subtraction is a challenging task. In this paper, we propose a pixel-based background subtraction method based on spatial similarity. The main difficulties of background subtraction include various background changes, shadows, and objects similar in color to background areas. In order to address these problems, we first computed the spatial similarity using the structural similarity method (SSIM). Spatial similarity is an effective way of eliminating shadows and detecting objects similar to the background areas. With spatial similarity, we roughly eliminated most background pixels such as shadows and moving background areas, while preserving objects that are similar to the background regions. Finally, the remaining pixels were classified as background pixels and foreground pixels using density estimation. Previous methods based on density estimation required high computational complexity. However, by selecting the minimum number of features and deleting most background pixels, we were able to significantly reduce the level of computational complexity. We compared our method with some existing background modeling methods. The experimental results show that the proposed method produced more accurate and stable results.

Original languageEnglish
Article number30
Pages (from-to)1-16
Number of pages16
JournalEurasip Journal on Image and Video Processing
Volume2014
Issue number1
DOIs
Publication statusPublished - 2014 Dec 1

Fingerprint

Pixels
Computational complexity
Computer vision
Color

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Electrical and Electronic Engineering

Cite this

@article{2c5e2074bc6b4413ac33bc9ff2868c98,
title = "Low-complexity background subtraction based on spatial similarity",
abstract = "Robust detection of moving objects from video sequences is an important task in machine vision systems and applications. To detect moving objects, accurate background subtraction is essential. In real environments, due to complex and various background types, background subtraction is a challenging task. In this paper, we propose a pixel-based background subtraction method based on spatial similarity. The main difficulties of background subtraction include various background changes, shadows, and objects similar in color to background areas. In order to address these problems, we first computed the spatial similarity using the structural similarity method (SSIM). Spatial similarity is an effective way of eliminating shadows and detecting objects similar to the background areas. With spatial similarity, we roughly eliminated most background pixels such as shadows and moving background areas, while preserving objects that are similar to the background regions. Finally, the remaining pixels were classified as background pixels and foreground pixels using density estimation. Previous methods based on density estimation required high computational complexity. However, by selecting the minimum number of features and deleting most background pixels, we were able to significantly reduce the level of computational complexity. We compared our method with some existing background modeling methods. The experimental results show that the proposed method produced more accurate and stable results.",
author = "Sangwook Lee and Lee, {Chul Hee}",
year = "2014",
month = "12",
day = "1",
doi = "10.1186/1687-5281-2014-30",
language = "English",
volume = "2014",
pages = "1--16",
journal = "Eurasip Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Publishing Company",
number = "1",

}

Low-complexity background subtraction based on spatial similarity. / Lee, Sangwook; Lee, Chul Hee.

In: Eurasip Journal on Image and Video Processing, Vol. 2014, No. 1, 30, 01.12.2014, p. 1-16.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Low-complexity background subtraction based on spatial similarity

AU - Lee, Sangwook

AU - Lee, Chul Hee

PY - 2014/12/1

Y1 - 2014/12/1

N2 - Robust detection of moving objects from video sequences is an important task in machine vision systems and applications. To detect moving objects, accurate background subtraction is essential. In real environments, due to complex and various background types, background subtraction is a challenging task. In this paper, we propose a pixel-based background subtraction method based on spatial similarity. The main difficulties of background subtraction include various background changes, shadows, and objects similar in color to background areas. In order to address these problems, we first computed the spatial similarity using the structural similarity method (SSIM). Spatial similarity is an effective way of eliminating shadows and detecting objects similar to the background areas. With spatial similarity, we roughly eliminated most background pixels such as shadows and moving background areas, while preserving objects that are similar to the background regions. Finally, the remaining pixels were classified as background pixels and foreground pixels using density estimation. Previous methods based on density estimation required high computational complexity. However, by selecting the minimum number of features and deleting most background pixels, we were able to significantly reduce the level of computational complexity. We compared our method with some existing background modeling methods. The experimental results show that the proposed method produced more accurate and stable results.

AB - Robust detection of moving objects from video sequences is an important task in machine vision systems and applications. To detect moving objects, accurate background subtraction is essential. In real environments, due to complex and various background types, background subtraction is a challenging task. In this paper, we propose a pixel-based background subtraction method based on spatial similarity. The main difficulties of background subtraction include various background changes, shadows, and objects similar in color to background areas. In order to address these problems, we first computed the spatial similarity using the structural similarity method (SSIM). Spatial similarity is an effective way of eliminating shadows and detecting objects similar to the background areas. With spatial similarity, we roughly eliminated most background pixels such as shadows and moving background areas, while preserving objects that are similar to the background regions. Finally, the remaining pixels were classified as background pixels and foreground pixels using density estimation. Previous methods based on density estimation required high computational complexity. However, by selecting the minimum number of features and deleting most background pixels, we were able to significantly reduce the level of computational complexity. We compared our method with some existing background modeling methods. The experimental results show that the proposed method produced more accurate and stable results.

UR - http://www.scopus.com/inward/record.url?scp=84950108088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84950108088&partnerID=8YFLogxK

U2 - 10.1186/1687-5281-2014-30

DO - 10.1186/1687-5281-2014-30

M3 - Article

VL - 2014

SP - 1

EP - 16

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

SN - 1687-5176

IS - 1

M1 - 30

ER -