The name INDECS is an acronym which stands for Indoor Environment under Changing conditionS. The database consists of several sets of pictures taken in five rooms of different functionality under various illumination and weather conditions at different periods of time. Each room was observed from many viewpoints and angles. Moreover, the normal activity in the rooms was recorded: people appear in the rooms, pieces of furniture are moved over time.
For references and a detailed description of the database, please see the Documents section. The database can be obtained from the Download section.
If you have any questions or you experience technical problems, please contact Andrzej Pronobis.
|
|
|
| |
|
The following technical report provides a detailed description of the INDECS database:
-
A. Pronobis and B. Caputo.
The KTH-INDECS database.
Technical Report CVAP298, Kungliga Tekniska Hoegskolan, CVAP, September 2005.
Publications using the database can be obtained below:
-
A. Pronobis, B. Caputo, P. Jensfelt, and H. I. Christensen.
A discriminative approach to robust visual place recognition.
In Proceedings of the IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS06), Beijing, China, October 2006.
-
A. Pronobis.
Indoor place recognition using support vector machines.
Master's thesis, NADA/CVAP, Kungliga Tekniska Hoegskolan, Stockholm, Sweden, December 2005.
If you use the INDECS database in your scientific work, please cite as:
|
|
|
| |
|
In order to facilitate downloading, the database was divided into several parts with respect to the room in which the images were taken as well as illumination conditions. The images are available in the PNG format in two resolutions: original 1024x768 and resampled to 512x384. Each part can be downloaded as one TAR archive. Windows users can use one of the available Windows TAR implementations such as BsdTar in order to decompress the archives.
|
|
|
|
Created by: Andrzej Pronobis
|
Last modified:
|
|
