View independent vehicle make and model recognition with virtual frontal view

Yukiko Shinozuka, Takuya Minagawa, Hideo Saito

Research output: Contribution to journalArticle

Abstract

This paper proposes a novel view independent vehicle make and model recognition method (VMMR). Our system identifies the make and model from the variety of viewpoints while the conventional methods for VMMR work only for the fixed frontal or rear images. In addition, it needs only the 2D images not CAD data for database. To solve the alignment issue, our method uses SIFT, that has scale and rotation invariance. For the view independent recognition, it creates less distorted frontal view images by view morphing or homography matrix calculated by the position of the license plate and extracts the keypoints from them. Our method enables to recognize up to 60-degree angle with high accuracy due to the less distorted virtual frontal images.

Original languageEnglish
JournalIEEJ Transactions on Electronics, Information and Systems
Volume134
Issue number2
DOIs
Publication statusPublished - 2014

Fingerprint

Invariance
Computer aided design

Keywords

  • Homography matrix
  • SIFT
  • Vehicle Make and Model Recognition
  • View Independent
  • View Morphing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

View independent vehicle make and model recognition with virtual frontal view. / Shinozuka, Yukiko; Minagawa, Takuya; Saito, Hideo.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 134, No. 2, 2014.

Research output: Contribution to journalArticle

@article{f74e5b5d4e40495397000bdc42dd23e1,
title = "View independent vehicle make and model recognition with virtual frontal view",
abstract = "This paper proposes a novel view independent vehicle make and model recognition method (VMMR). Our system identifies the make and model from the variety of viewpoints while the conventional methods for VMMR work only for the fixed frontal or rear images. In addition, it needs only the 2D images not CAD data for database. To solve the alignment issue, our method uses SIFT, that has scale and rotation invariance. For the view independent recognition, it creates less distorted frontal view images by view morphing or homography matrix calculated by the position of the license plate and extracts the keypoints from them. Our method enables to recognize up to 60-degree angle with high accuracy due to the less distorted virtual frontal images.",
keywords = "Homography matrix, SIFT, Vehicle Make and Model Recognition, View Independent, View Morphing",
author = "Yukiko Shinozuka and Takuya Minagawa and Hideo Saito",
year = "2014",
doi = "10.1541/ieejeiss.134.233",
language = "English",
volume = "134",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "2",

}

TY - JOUR

T1 - View independent vehicle make and model recognition with virtual frontal view

AU - Shinozuka, Yukiko

AU - Minagawa, Takuya

AU - Saito, Hideo

PY - 2014

Y1 - 2014

N2 - This paper proposes a novel view independent vehicle make and model recognition method (VMMR). Our system identifies the make and model from the variety of viewpoints while the conventional methods for VMMR work only for the fixed frontal or rear images. In addition, it needs only the 2D images not CAD data for database. To solve the alignment issue, our method uses SIFT, that has scale and rotation invariance. For the view independent recognition, it creates less distorted frontal view images by view morphing or homography matrix calculated by the position of the license plate and extracts the keypoints from them. Our method enables to recognize up to 60-degree angle with high accuracy due to the less distorted virtual frontal images.

AB - This paper proposes a novel view independent vehicle make and model recognition method (VMMR). Our system identifies the make and model from the variety of viewpoints while the conventional methods for VMMR work only for the fixed frontal or rear images. In addition, it needs only the 2D images not CAD data for database. To solve the alignment issue, our method uses SIFT, that has scale and rotation invariance. For the view independent recognition, it creates less distorted frontal view images by view morphing or homography matrix calculated by the position of the license plate and extracts the keypoints from them. Our method enables to recognize up to 60-degree angle with high accuracy due to the less distorted virtual frontal images.

KW - Homography matrix

KW - SIFT

KW - Vehicle Make and Model Recognition

KW - View Independent

KW - View Morphing

UR - http://www.scopus.com/inward/record.url?scp=84893318136&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893318136&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.134.233

DO - 10.1541/ieejeiss.134.233

M3 - Article

VL - 134

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 2

ER -