Recognising panoramas

Matthew Brown; D G Lowe

doi:10.1109/ICCV.2003.1238630

Recognising panoramas

Matthew Brown, D G Lowe

Department of Computer Science

Research output: Contribution to conference › Paper › peer-review

914 Citations (SciVal)

Abstract

The problem considered in this paper is the fully automatic construction of panoramas. Fundamentally, this problem requires recognition, as we need to know which parts of the panorama join up. Previous approaches have used human input or restrictions on the image sequence for the matching step. In this work we use object recognition techniques based on invariant local features to select matching images, and a probabilistic model for verification. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the images. It is also insensitive to 'noise' images which are not part of the panorama at all, that is, it recognises panoramas. This suggests a useful application for photographers: the system takes as input the images on an entire flash card or film, recognises images that form part of a panorama, and stitches them with no user input whatsoever.

Original language	English
Pages	1218-1225
Number of pages	8
DOIs	https://doi.org/10.1109/ICCV.2003.1238630
Publication status	Published - Oct 2003
Event	Computer Vision 2003: Ninth IEEE International Conference on - Nice, France Duration: 13 Oct 2003 → 16 Oct 2003

Conference

Conference	Computer Vision 2003: Ninth IEEE International Conference on
Country/Territory	France
City	Nice
Period	13/10/03 → 16/10/03

Access to Document

10.1109/ICCV.2003.1238630

Cite this

@conference{b5f1a2df360643109970a5d61e1a47bd,

title = "Recognising panoramas",

abstract = "The problem considered in this paper is the fully automatic construction of panoramas. Fundamentally, this problem requires recognition, as we need to know which parts of the panorama join up. Previous approaches have used human input or restrictions on the image sequence for the matching step. In this work we use object recognition techniques based on invariant local features to select matching images, and a probabilistic model for verification. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the images. It is also insensitive to 'noise' images which are not part of the panorama at all, that is, it recognises panoramas. This suggests a useful application for photographers: the system takes as input the images on an entire flash card or film, recognises images that form part of a panorama, and stitches them with no user input whatsoever.",

author = "Matthew Brown and Lowe, {D G}",

year = "2003",

month = oct,

doi = "10.1109/ICCV.2003.1238630",

language = "English",

pages = "1218--1225",

note = "Computer Vision 2003: Ninth IEEE International Conference on ; Conference date: 13-10-2003 Through 16-10-2003",

}

TY - CONF

T1 - Recognising panoramas

AU - Brown, Matthew

AU - Lowe, D G

PY - 2003/10

Y1 - 2003/10

N2 - The problem considered in this paper is the fully automatic construction of panoramas. Fundamentally, this problem requires recognition, as we need to know which parts of the panorama join up. Previous approaches have used human input or restrictions on the image sequence for the matching step. In this work we use object recognition techniques based on invariant local features to select matching images, and a probabilistic model for verification. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the images. It is also insensitive to 'noise' images which are not part of the panorama at all, that is, it recognises panoramas. This suggests a useful application for photographers: the system takes as input the images on an entire flash card or film, recognises images that form part of a panorama, and stitches them with no user input whatsoever.

AB - The problem considered in this paper is the fully automatic construction of panoramas. Fundamentally, this problem requires recognition, as we need to know which parts of the panorama join up. Previous approaches have used human input or restrictions on the image sequence for the matching step. In this work we use object recognition techniques based on invariant local features to select matching images, and a probabilistic model for verification. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the images. It is also insensitive to 'noise' images which are not part of the panorama at all, that is, it recognises panoramas. This suggests a useful application for photographers: the system takes as input the images on an entire flash card or film, recognises images that form part of a panorama, and stitches them with no user input whatsoever.

UR - http://dx.doi.org/10.1109/ICCV.2003.1238630

U2 - 10.1109/ICCV.2003.1238630

DO - 10.1109/ICCV.2003.1238630

M3 - Paper

SP - 1218

EP - 1225

T2 - Computer Vision 2003: Ninth IEEE International Conference on

Y2 - 13 October 2003 through 16 October 2003

ER -

Recognising panoramas

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this