Limits...
Basic level scene understanding: categories, attributes and structures.

Xiao J, Hays J, Russell BC, Patterson G, Ehinger KA, Torralba A, Oliva A - Front Psychol (2013)

Bottom Line: This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition.We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition.Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

View Article: PubMed Central - PubMed

Affiliation: Computer Science, Princeton University Princeton, NJ, USA.

ABSTRACT
A longstanding goal of computer vision is to build a system that can automatically understand a 3D scene from a single image. This requires extracting semantic concepts and 3D information from 2D images which can depict an enormous variety of environments that comprise our visual world. This paper summarizes our recent efforts toward these goals. First, we describe the richly annotated SUN database which is a collection of annotated images spanning 908 different scene categories with object, attribute, and geometric labels for many scenes. This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition. We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition. Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

No MeSH data available.


To demonstrate intra-category object variation within the SUN database, these are samples of the 12,839 chairs that were manually annotated in 3500 images.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3756302&req=5

Figure 4: To demonstrate intra-category object variation within the SUN database, these are samples of the 12,839 chairs that were manually annotated in 3500 images.

Mentions: Supporting these research efforts is the Scene UNderstanding (SUN) database. By modern standards, the SUN database is not especially large, containing on the order of 100,000 scenes. But the SUN database is, instead, richly annotated with scene categories, scene attributes, geometric properties, “memorability” measurements (Isola et al., 2011), and object segmentations. There are 326,582 manually segmented objects for the 5650 object categories labeled (Barriuso and Torralba, 2012). Object categories are visualized in Figure 1 and annotated objects are shown in Figures 2, 3, and 4. We believe the SUN database is the largest database from which one can learn the relationship among these object and scene properties. This combination of scene diversity and rich annotation is important for scaling scene understanding algorithms to work in the real world.


Basic level scene understanding: categories, attributes and structures.

Xiao J, Hays J, Russell BC, Patterson G, Ehinger KA, Torralba A, Oliva A - Front Psychol (2013)

To demonstrate intra-category object variation within the SUN database, these are samples of the 12,839 chairs that were manually annotated in 3500 images.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3756302&req=5

Figure 4: To demonstrate intra-category object variation within the SUN database, these are samples of the 12,839 chairs that were manually annotated in 3500 images.
Mentions: Supporting these research efforts is the Scene UNderstanding (SUN) database. By modern standards, the SUN database is not especially large, containing on the order of 100,000 scenes. But the SUN database is, instead, richly annotated with scene categories, scene attributes, geometric properties, “memorability” measurements (Isola et al., 2011), and object segmentations. There are 326,582 manually segmented objects for the 5650 object categories labeled (Barriuso and Torralba, 2012). Object categories are visualized in Figure 1 and annotated objects are shown in Figures 2, 3, and 4. We believe the SUN database is the largest database from which one can learn the relationship among these object and scene properties. This combination of scene diversity and rich annotation is important for scaling scene understanding algorithms to work in the real world.

Bottom Line: This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition.We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition.Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

View Article: PubMed Central - PubMed

Affiliation: Computer Science, Princeton University Princeton, NJ, USA.

ABSTRACT
A longstanding goal of computer vision is to build a system that can automatically understand a 3D scene from a single image. This requires extracting semantic concepts and 3D information from 2D images which can depict an enormous variety of environments that comprise our visual world. This paper summarizes our recent efforts toward these goals. First, we describe the richly annotated SUN database which is a collection of annotated images spanning 908 different scene categories with object, attribute, and geometric labels for many scenes. This database allows us to systematically study the space of scenes and to establish a benchmark for scene and object recognition. We augment the categorical SUN database with 102 scene attributes for every image and explore attribute recognition. Finally, we present an integrated system to extract the 3D structure of the scene and objects depicted in an image.

No MeSH data available.