Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

DMCA

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope (2001)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Aude Oliva , Antonio Torralba

Venue:	International Journal of Computer Vision
Citations:	1311 - 81 self

BibTeX

@ARTICLE{Oliva01modelingthe,
    author = {Aude Oliva and Antonio Torralba},
    title = {Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope},
    journal = {International Journal of Computer Vision},
    year = {2001},
    volume = {42},
    pages = {145--175}
}

OpenURL

Abstract

In this paper, we propose a computational model of the recognition of real world scenes that bypasses the segmentation and the processing of individual objects or regions. The procedure is based on a very low dimensional representation of the scene, that we term the Spatial Envelope. We propose a set of perceptual dimensions (naturalness, openness, roughness, expansion, ruggedness) that represent the dominant spatial structure of a scene. Then, we show that these dimensions may be reliably estimated using spectral and coarsely localized information. The model generates a multidimensional space in which scenes sharing membership in semantic categories (e.g., streets, highways, coasts) are projected closed together. The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.

Keyphrases

spatial envelope holistic representation perceptual dimension specific information dominant spatial structure real world scene individual object spatial envelope model semantic category scene categorization localized information probable semantic category low dimensional representation computational model object shape multidimensional space

DMCA