Efficient Localization of Panoramic Images Using Tiled Image Descriptors

• Item type: Trans(1)
• 公開日: 2014-07-25
• タイトル: Efficient Localization of Panoramic Images Using Tiled Image Descriptors
• タイトル / 言語: en
• タイトル: Efficient Localization of Panoramic Images Using Tiled Image Descriptors
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [Resarch Paper - Express Paper] visual place recognition, bag of visual words and VLAD image representations, panorama image localization
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology
• 著者所属: Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology
• 著者所属: Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology
• 著者所属: WILLOW project, Laboratoire d'Informatique de l'Ecole Normale Superieure, ENS/INRIA/CNRS UMR 8548
• 著者所属: Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Enginnering, Czech Technical University in Prague
• 著者所属(英): en
• 著者所属(英): Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Department of Mechanical and Control Engineering, Graduate School of Science and Engineering, Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): WILLOW project, Laboratoire d'Informatique de l'Ecole Normale Superieure, ENS/INRIA/CNRS UMR 8548
• 著者所属(英): en
• 著者所属(英): Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Enginnering, Czech Technical University in Prague
• 著者名: Akihiko, Torii; Yafei, Dong; Masatoshi, Okutomi; Josef, Sivic; Tomas, Pajdla
• 著者名(英): Akihiko, Torii; Yafei, Dong; Masatoshi, Okutomi; Josef, Sivic; Tomas, Pajdla
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: We seek to localize a query panorama with a wide field of view given a large database of street-level geotagged imagery. This is a challenging task because of significant changes in appearance due to viewpoint, season, occluding people or newly constructed buildings. An additional key challenge is the computational and memory efficiency due to the planet-scale size of the available geotagged image databases. The contributions of this paper are two-fold. First, we develop a compact image representation for scalable retrieval of panoramic images that represents each panorama as an ordered set of vertical image tiles. Two panoramas are matched by efficiently searching for their optimal horizontal alignment, while respecting the tile ordering constraint. Second, we collect a new challenging query test dataset from Shibuya, Tokyo containing more than thousand panoramic and perspective query images with manually verified ground truth geolocation. We demonstrate significant improvements of the proposed method compared to the standard bag-of-visual-words and VLAD baselines.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: We seek to localize a query panorama with a wide field of view given a large database of street-level geotagged imagery. This is a challenging task because of significant changes in appearance due to viewpoint, season, occluding people or newly constructed buildings. An additional key challenge is the computational and memory efficiency due to the planet-scale size of the available geotagged image databases. The contributions of this paper are two-fold. First, we develop a compact image representation for scalable retrieval of panoramic images that represents each panorama as an ordered set of vertical image tiles. Two panoramas are matched by efficiently searching for their optimal horizontal alignment, while respecting the tile ordering constraint. Second, we collect a new challenging query test dataset from Shibuya, Tokyo containing more than thousand panoramic and perspective query images with manually verified ground truth geolocation. We demonstrate significant improvements of the proposed method compared to the standard bag-of-visual-words and VLAD baselines.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12628065
• 書誌情報: IPSJ Transactions on Computer Vision and Applications （CVA）; 巻 6, p. 58-62, 発行日 2014-07-25
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-6695
• 出版者 / 言語: ja
• 出版者: 情報処理学会