Novel vehicle detection system based on stacked DoG kernel and AdaBoost

Hyun Ho Kang, Seo Won Lee, Sung Hyun You, Choon Ki Ahn

Research output: Contribution to journalArticle

Abstract

This paper proposes a novel vehicle detection system that can overcome some limitations of typical vehicle detection systems using AdaBoost-based methods. The performance of the AdaBoost-based vehicle detection system is dependent on its training data. Thus, its performance decreases when the shape of a target differs from its training data, or the pattern of a preceding vehicle is not visible in the image due to the light conditions. A stacked Difference of Gaussian (DoG)–based feature extraction algorithm is proposed to address this issue by recognizing common characteristics, such as the shadow and rear wheels beneath vehicles—of vehicles under various conditions. The common characteristics of vehicles are extracted by applying the stacked DoG shaped kernel obtained from the 3D plot of an image through a convolution method and investigating only certain regions that have a similar patterns. A new vehicle detection system is constructed by combining the novel stacked DoG feature extraction algorithm with the AdaBoost method. Experiments are provided to demonstrate the effectiveness of the proposed vehicle detection system under different conditions.

Original languageEnglish
Article numbere0193733
JournalPLoS One
Volume13
Issue number3
DOIs
Publication statusPublished - 2018 Mar 1

Fingerprint

Adaptive boosting
seeds
Light
Feature extraction
wheels
Convolution
Wheels
methodology

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Novel vehicle detection system based on stacked DoG kernel and AdaBoost. / Kang, Hyun Ho; Lee, Seo Won; You, Sung Hyun; Ahn, Choon Ki.

In: PLoS One, Vol. 13, No. 3, e0193733, 01.03.2018.

Research output: Contribution to journalArticle

Kang, Hyun Ho ; Lee, Seo Won ; You, Sung Hyun ; Ahn, Choon Ki. / Novel vehicle detection system based on stacked DoG kernel and AdaBoost. In: PLoS One. 2018 ; Vol. 13, No. 3.
@article{9934b4d0b8ab4f4ab8e6d7a12985f592,
title = "Novel vehicle detection system based on stacked DoG kernel and AdaBoost",
abstract = "This paper proposes a novel vehicle detection system that can overcome some limitations of typical vehicle detection systems using AdaBoost-based methods. The performance of the AdaBoost-based vehicle detection system is dependent on its training data. Thus, its performance decreases when the shape of a target differs from its training data, or the pattern of a preceding vehicle is not visible in the image due to the light conditions. A stacked Difference of Gaussian (DoG)–based feature extraction algorithm is proposed to address this issue by recognizing common characteristics, such as the shadow and rear wheels beneath vehicles—of vehicles under various conditions. The common characteristics of vehicles are extracted by applying the stacked DoG shaped kernel obtained from the 3D plot of an image through a convolution method and investigating only certain regions that have a similar patterns. A new vehicle detection system is constructed by combining the novel stacked DoG feature extraction algorithm with the AdaBoost method. Experiments are provided to demonstrate the effectiveness of the proposed vehicle detection system under different conditions.",
author = "Kang, {Hyun Ho} and Lee, {Seo Won} and You, {Sung Hyun} and Ahn, {Choon Ki}",
year = "2018",
month = "3",
day = "1",
doi = "10.1371/journal.pone.0193733",
language = "English",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

TY - JOUR

T1 - Novel vehicle detection system based on stacked DoG kernel and AdaBoost

AU - Kang, Hyun Ho

AU - Lee, Seo Won

AU - You, Sung Hyun

AU - Ahn, Choon Ki

PY - 2018/3/1

Y1 - 2018/3/1

N2 - This paper proposes a novel vehicle detection system that can overcome some limitations of typical vehicle detection systems using AdaBoost-based methods. The performance of the AdaBoost-based vehicle detection system is dependent on its training data. Thus, its performance decreases when the shape of a target differs from its training data, or the pattern of a preceding vehicle is not visible in the image due to the light conditions. A stacked Difference of Gaussian (DoG)–based feature extraction algorithm is proposed to address this issue by recognizing common characteristics, such as the shadow and rear wheels beneath vehicles—of vehicles under various conditions. The common characteristics of vehicles are extracted by applying the stacked DoG shaped kernel obtained from the 3D plot of an image through a convolution method and investigating only certain regions that have a similar patterns. A new vehicle detection system is constructed by combining the novel stacked DoG feature extraction algorithm with the AdaBoost method. Experiments are provided to demonstrate the effectiveness of the proposed vehicle detection system under different conditions.

AB - This paper proposes a novel vehicle detection system that can overcome some limitations of typical vehicle detection systems using AdaBoost-based methods. The performance of the AdaBoost-based vehicle detection system is dependent on its training data. Thus, its performance decreases when the shape of a target differs from its training data, or the pattern of a preceding vehicle is not visible in the image due to the light conditions. A stacked Difference of Gaussian (DoG)–based feature extraction algorithm is proposed to address this issue by recognizing common characteristics, such as the shadow and rear wheels beneath vehicles—of vehicles under various conditions. The common characteristics of vehicles are extracted by applying the stacked DoG shaped kernel obtained from the 3D plot of an image through a convolution method and investigating only certain regions that have a similar patterns. A new vehicle detection system is constructed by combining the novel stacked DoG feature extraction algorithm with the AdaBoost method. Experiments are provided to demonstrate the effectiveness of the proposed vehicle detection system under different conditions.

UR - http://www.scopus.com/inward/record.url?scp=85042946321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042946321&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0193733

DO - 10.1371/journal.pone.0193733

M3 - Article

C2 - 29513727

AN - SCOPUS:85042946321

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e0193733

ER -