疑似正面画像を用いた視点によらない車名判別

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2014/02/01

タイトル(英語): View Independent Vehicle Make and Model Recognition with Virtual Frontal View

著者名: 篠塚　祐紀子（慶應義塾大学大学院理工学研究科），皆川　卓也（慶應義塾大学大学院理工学研究科），斎藤　英雄（慶應義塾大学大学院理工学研究科）

著者名(英語): Yukiko Shinozuka (Keio Graduate School of Science and Technology), Takuya Minagawa (Keio Graduate School of Science and Technology), Hideo Saito (Keio Graduate School of Science and Technology)

キーワード: 車名判別，SIFT特徴量，自由視点，View Morphing，平面射影変換行列　　Vehicle Make and Model Recognition，SIFT，View Independent，View Morphing，Homography matrix

要約(英語): 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.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.134 No.2 （2014） 特集：知覚情報技術の最前線

本誌掲載ページ: 233-241 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/134/2/134_233/_article/-char/ja/