SUN database: Large-scale scene recognition from abbey to zoo

Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object categorization contain hundre...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 3485 - 3492
Main Authors Jianxiong Xiao, Hays, J, Ehinger, K A, Oliva, A, Torralba, A
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2010
Subjects
Anthropometry
Bridges
Computer vision
Humans
Image databases
Large-scale systems
Layout
Legged locomotion
Spatial databases
Sun
Online AccessGet full text
ISBN1424469848
9781424469840
ISSN1063-6919
1063-6919
DOI10.1109/CVPR.2010.5539970

Cover

More Information
Summary:Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object categorization contain hundreds of different classes of objects, the largest available dataset of scene categories contains only 15 classes. In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. We use 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of performance. We measure human scene classification performance on the SUN database and compare this with computational methods. Additionally, we study a finer-grained scene representation to detect scenes embedded inside of larger scenes.
ISBN:1424469848
9781424469840
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2010.5539970