A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance

Giyoung Lee; Rammohan Mallipeddi; Gil Jin Jang; Minho Lee

doi:10.1109/LSP.2015.2417592

A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance

Giyoung Lee, Rammohan Mallipeddi, Gil Jin Jang, Minho Lee

School of Electronics Engineering

Kyungpook National University

Research output: Contribution to journal › Article › peer-review

42 Scopus citations

Abstract

Recent developments in vision systems such as distributed smart cameras have encouraged researchers to develop advanced computer vision applications suitable to embedded platforms. In the embedded surveillance system, where memory and computing resources are limited, simple and efficient computer vision algorithms are required. In this letter, we present a moving object detection method for real-time traffic surveillance applications. The proposed method is a combination of a genetic dynamic saliency map (GDSM), which is an improved version of dynamic saliency map (DSM) and background subtraction. The experimental results show the effectiveness of the proposed method in detecting moving objects.

Original language	English
Article number	7072530
Pages (from-to)	1619-1622
Number of pages	4
Journal	IEEE Signal Processing Letters
Volume	22
Issue number	10
DOIs	https://doi.org/10.1109/LSP.2015.2417592
State	Published - 1 Oct 2015

Keywords

Background subtraction
dynamic saliency map
genetic algorithm
object detection
real-time traffic surveillance system

Access to Document

10.1109/LSP.2015.2417592

Cite this

@article{10ad2efbc977486687a80d909ab899c8,

title = "A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance",

abstract = "Recent developments in vision systems such as distributed smart cameras have encouraged researchers to develop advanced computer vision applications suitable to embedded platforms. In the embedded surveillance system, where memory and computing resources are limited, simple and efficient computer vision algorithms are required. In this letter, we present a moving object detection method for real-time traffic surveillance applications. The proposed method is a combination of a genetic dynamic saliency map (GDSM), which is an improved version of dynamic saliency map (DSM) and background subtraction. The experimental results show the effectiveness of the proposed method in detecting moving objects.",

keywords = "Background subtraction, dynamic saliency map, genetic algorithm, object detection, real-time traffic surveillance system",

author = "Giyoung Lee and Rammohan Mallipeddi and Jang, {Gil Jin} and Minho Lee",

note = "Publisher Copyright: {\textcopyright} 1994-2012 IEEE.",

year = "2015",

month = oct,

day = "1",

doi = "10.1109/LSP.2015.2417592",

language = "English",

volume = "22",

pages = "1619--1622",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance

AU - Lee, Giyoung

AU - Mallipeddi, Rammohan

AU - Jang, Gil Jin

AU - Lee, Minho

PY - 2015/10/1

Y1 - 2015/10/1

N2 - Recent developments in vision systems such as distributed smart cameras have encouraged researchers to develop advanced computer vision applications suitable to embedded platforms. In the embedded surveillance system, where memory and computing resources are limited, simple and efficient computer vision algorithms are required. In this letter, we present a moving object detection method for real-time traffic surveillance applications. The proposed method is a combination of a genetic dynamic saliency map (GDSM), which is an improved version of dynamic saliency map (DSM) and background subtraction. The experimental results show the effectiveness of the proposed method in detecting moving objects.

AB - Recent developments in vision systems such as distributed smart cameras have encouraged researchers to develop advanced computer vision applications suitable to embedded platforms. In the embedded surveillance system, where memory and computing resources are limited, simple and efficient computer vision algorithms are required. In this letter, we present a moving object detection method for real-time traffic surveillance applications. The proposed method is a combination of a genetic dynamic saliency map (GDSM), which is an improved version of dynamic saliency map (DSM) and background subtraction. The experimental results show the effectiveness of the proposed method in detecting moving objects.

KW - Background subtraction

KW - dynamic saliency map

KW - genetic algorithm

KW - object detection

KW - real-time traffic surveillance system

UR - http://www.scopus.com/inward/record.url?scp=84927617532&partnerID=8YFLogxK

U2 - 10.1109/LSP.2015.2417592

DO - 10.1109/LSP.2015.2417592

M3 - Article

AN - SCOPUS:84927617532

SN - 1070-9908

VL - 22

SP - 1619

EP - 1622

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 10

M1 - 7072530

ER -

A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this