Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7236Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.creator | Torralba, Antonio | - |
| dc.creator | Sinha, Pawan | - |
| dc.date | 2004-10-20T21:03:41Z | - |
| dc.date | 2004-10-20T21:03:41Z | - |
| dc.date | 2001-07-25 | - |
| dc.date.accessioned | 2013-10-09T02:48:37Z | - |
| dc.date.available | 2013-10-09T02:48:37Z | - |
| dc.date.issued | 2013-10-09 | - |
| dc.identifier | AIM-2001-015 | - |
| dc.identifier | CBCL-202 | - |
| dc.identifier | http://hdl.handle.net/1721.1/7236 | - |
| dc.identifier.uri | http://koha.mediu.edu.my:8181/xmlui/handle/1721 | - |
| dc.description | We propose a scheme for indoor place identification based on the recognition of global scene views. Scene views are encoded using a holistic representation that provides low-resolution spatial and spectral information. The holistic nature of the representation dispenses with the need to rely on specific objects or local landmarks and also renders it robust against variations in object configurations. We demonstrate the scheme on the problem of recognizing scenes in video sequences captured while walking through an office environment. We develop a method for distinguishing between 'diagnostic' and 'generic' views and also evaluate changes in system performances as a function of the amount of training data available and the complexity of the representation. | - |
| dc.format | 17 p. | - |
| dc.format | 14931961 bytes | - |
| dc.format | 3219314 bytes | - |
| dc.format | application/postscript | - |
| dc.format | application/pdf | - |
| dc.language | en_US | - |
| dc.relation | AIM-2001-015 | - |
| dc.relation | CBCL-202 | - |
| dc.subject | AI | - |
| dc.subject | Scene classification | - |
| dc.subject | Navigation | - |
| dc.subject | scene representation | - |
| dc.title | Recognizing Indoor Scenes | - |
| Appears in Collections: | MIT Items | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.