Dataset download page
Click on images below to download zip files.
Note: The zip-files total at 23GB.
Each file is between 300MB and 1GB in size.
In order to download all files at once, you may use the Linux command
wget. E.g.
wget -nd -nc -r -l 0 http://www.cvl.isy.liu.se/research/objrec/posedb/datasets.html
Note: this will download the zip-files, as well as the html, and png images on this web-page.
Dataset 1
35InchBayFront
![](img/Obj1_black.png)
![](img/Obj1_cluttered.png)
AutoFuse
![](img/Obj2_black.png)
![](img/Obj2_cluttered.png)
CableBoxGreen
![](img/Obj3_black.png)
![](img/Obj3_cluttered.png)
HoseClamp
![](img/Obj4_black.png)
![](img/Obj4_cluttered.png)
House
![](img/Obj5_black.png)
![](img/Obj5_cluttered.png)
House (light setting 2)
![](img/Obj5L2_black.png)
![](img/Obj5L2_cluttered.png)
House (light setting 3)
![](img/Obj5L3_black.png)
![](img/Obj5L3_cluttered.png)
InstallationCapOrange
![](img/Obj6_black.png)
![](img/Obj6_cluttered.png)
Ipipe
![](img/Obj7_black.png)
![](img/Obj7_cluttered.png)
MouseTrap
![](img/Obj8_black.png)
![](img/Obj8_cluttered.png)
PowerSocketRedInside
![](img/Obj9_black.png)
![](img/Obj9_cluttered.png)
PowerSocketRedOutside
![](img/Obj10_black.png)
![](img/Obj10_cluttered.png)
SCSIAdapter
![](img/Obj11_black.png)
![](img/Obj11_cluttered.png)
Tpipe
![](img/Obj12_black.png)
![](img/Obj12_cluttered.png)
TriangleWood
![](img/Obj13_black.png)
![](img/Obj13_cluttered.png)
VolvoC70Gold
![](img/Obj14_black.png)
![](img/Obj14_cluttered.png)
VolvoPoliceWhite
![](img/Obj15_black.png)
![](img/Obj15_cluttered.png)
VolvoV70Red
![](img/Obj16_black.png)
![](img/Obj16_cluttered.png)
Dataset 2
VolvoZoom
![](img/VolvoZoom.png)
There is just one zip file for the above images!
Dataset 3
VolvoMovingLight
![](img/VolvoMovingLight.png)
There is just one zip file for the above images!
Trainingset for datasets 2 & 3
VolvoOldBlack
![](img/VolvoC70__Curve_030_Rot_090.png.jpg)
Associated publication
If you use this database in a publication, you should reference the paper:
F. Viksten, P.-E. Forssén, B. Johansson, and A. Moe.
Comparison of Local Image Descriptors for Full 6 Degree-of-Freedom Pose Estimation.
IEEE International Conference on Robotics and Automation, May 2009. [BibTeX].
Back to main dataset page.
Last updated: 2020-12-10