Indoor Scene Classification using combined 3D and Gist Features

Swadzba A, Wachsmuth S (2011)
In: Computer Vision - ACCV 2010. Lecture Notes in Computer Science, 6493, . Berlin, Heidelberg: Springer: 201-215.

Download
Restricted
Conference Paper | Published | English
Abstract
Scene categorization is an important mechanism for providing high-level context which can guide methods for a more detailed analysis of scenes. State-of-the-art techniques like Torralba’s Gist features show a good performance on categorizing outdoor scenes but have problems in categorizing indoor scenes. In contrast to object based approaches, we propose a 3D feature vector capturing general properties of the spatial layout of indoor scenes like shape and size of extracted planar patches and their orientation to each other. This idea is supported by psychological experiments which give evidence for the special role of 3D geometry in categorizing indoor scenes. In order to study the in uence of the 3D geometry we introduce in this paper a novel 3D indoor database and a method for de ning 3D features on planar surfaces extracted in 3D data. Additionally, we propose a voting technique to fuse 3D features and 2D Gist features and show in our experiments a signi cant contribution of the 3D features to the indoor scene categorization task.
Publishing Year
Conference
Asian Conference on Computer Vision
Location
Queenstown, New Zealand
Conference Date
2010-11-08 – 2010-11-12
PUB-ID

Cite this

Swadzba A, Wachsmuth S. Indoor Scene Classification using combined 3D and Gist Features. In: Computer Vision - ACCV 2010. Lecture Notes in Computer Science, 6493. Berlin, Heidelberg: Springer; 2011: 201-215.
Swadzba, A., & Wachsmuth, S. (2011). Indoor Scene Classification using combined 3D and Gist Features. Computer Vision - ACCV 2010, 201-215.
Swadzba, A., and Wachsmuth, S. (2011). “Indoor Scene Classification using combined 3D and Gist Features” in Computer Vision - ACCV 2010 Lecture Notes in Computer Science, 6493 (Berlin, Heidelberg: Springer), 201-215.
Swadzba, A., & Wachsmuth, S., 2011. Indoor Scene Classification using combined 3D and Gist Features. In Computer Vision - ACCV 2010. Lecture Notes in Computer Science, 6493. Berlin, Heidelberg: Springer, pp. 201-215.
A. Swadzba and S. Wachsmuth, “Indoor Scene Classification using combined 3D and Gist Features”, Computer Vision - ACCV 2010, Lecture Notes in Computer Science, 6493, Berlin, Heidelberg: Springer, 2011, pp.201-215.
Swadzba, A., Wachsmuth, S.: Indoor Scene Classification using combined 3D and Gist Features. Computer Vision - ACCV 2010. Lecture Notes in Computer Science, 6493. p. 201-215. Springer, Berlin, Heidelberg (2011).
Swadzba, Agnes, and Wachsmuth, Sven. “Indoor Scene Classification using combined 3D and Gist Features”. Computer Vision - ACCV 2010. Berlin, Heidelberg: Springer, 2011. Lecture Notes in Computer Science, 6493. 201-215.
Main File(s)
Access Level
Restricted Closed Access
Last Uploaded
2014-01-20 11:04:21

This data publication is cited in the following publications:
This publication cites the following data publications:
2639459
3D Indoor Scenes Database
Swadzba A, Wachsmuth S (2009)
Bielefeld University.

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search