Jacobs Robotics Object Discovery Dataset


Annotated RGB-D point clouds of everyday objects
from unstructured indoor scenes

In a plethora of robotic tasks like in service or industrial robotics, such as pick and place in households or unloading goods from shipping containers, visuoperceptual capabilities are required to detect objects with a large variety of appearances. Objects can appear in varying shapes, spatial dimensions, texture-content or with occlusions. Also in such tasks it may not be feasible to be aware of a vast set of object models beforehand for detection or manipulation purposes. Therefore, the discovery of unknown objects in unstructured scenes is an interesting and challenging research topic in robotics. Approaches which cope with such detection problem require real annotated sensor data to conduct adequate experiments to assess their performance.

The dataset (Object Discovery Dataset - ODD) is established and made here available for evaluation purposes. It consists of scenes which are captured by a Kinect-like RGB-D camera based on structured light principle in a resolution of 640x480 points. The scenes range from table-tops to unstructured scenes with a variety of simple and complex-shaped objects which are contacted, stacked or occluded like e.g. on shelves. The dataset consists of simple-shaped objects like boxes, cans or cones, and complex-shaped objects like teddy-bears, cordless drills, electric irons, binoculars or jars. In total 296 human-annotated objects in 30 scenes were captured.
Each scene consists of

  • a color intensity image file in PNG format,
  • a point cloud file in PCD format using the augmented 3D point type with RGB color and label information (cf. Point Cloud Library, pcl::PointXYZRGBL). Each point is labeled by a non-zero positive integer which corresponds to the object candidate label in the point cloud. Points annotated as zero represent background,
  • a semantic information file in XML format (How-to read the XML file). It currently consists of information whether the respective object is simple or complex-shaped.

The dataset is available as object_discovery_dataset_v0_1.tar.gz or object_discovery_dataset_v0_1.zip and is part of the work presented in

Christian A. Mueller and Andreas Birk
"Hierarchical Graph-Based Discovery of Non-Primitive-Shaped Objects in Unstructured Environments"
In IEEE International Conference on Robotics and Automation (ICRA), May 2016.

Please cite the paper (Bibtex file) if you use the dataset. Contributions to the dataset are welcome! Please contact us.
Contact: Christian A. Mueller [chr.mueller(at)jacobs-university.de]


In the following scene previews are displayed (for a proper rendering your browser requires WebGL support).

Sample name: scene3

Point cloud (view) : 11 MB

View

Sample name: scene23

Point cloud (view) : 11 MB

View

Sample name: scene27

Point cloud (view) : 11 MB

View

Sample name: scene10

Point cloud (view) : 11 MB

View

Sample name: scene25

Point cloud (view) : 11 MB

View

Sample name: scene5

Point cloud (view) : 11 MB

View

Sample name: scene30

Point cloud (view) : 11 MB

View

Sample name: scene4

Point cloud (view) : 11 MB

View

Sample name: scene17

Point cloud (view) : 11 MB

View

Sample name: scene7

Point cloud (view) : 11 MB

View

Sample name: scene19

Point cloud (view) : 11 MB

View

Sample name: scene2

Point cloud (view) : 11 MB

View

Sample name: scene15

Point cloud (view) : 11 MB

View

Sample name: scene1

Point cloud (view) : 11 MB

View

Sample name: scene11

Point cloud (view) : 11 MB

View

Sample name: scene28

Point cloud (view) : 11 MB

View

Sample name: scene22

Point cloud (view) : 11 MB

View

Sample name: scene26

Point cloud (view) : 11 MB

View

Sample name: scene6

Point cloud (view) : 11 MB

View

Sample name: scene9

Point cloud (view) : 11 MB

View

Sample name: scene20

Point cloud (view) : 11 MB

View

Sample name: scene14

Point cloud (view) : 11 MB

View

Sample name: scene13

Point cloud (view) : 11 MB

View

Sample name: scene16

Point cloud (view) : 11 MB

View

Sample name: scene12

Point cloud (view) : 11 MB

View

Sample name: scene18

Point cloud (view) : 11 MB

View

Sample name: scene24

Point cloud (view) : 11 MB

View

Sample name: scene21

Point cloud (view) : 11 MB

View

Sample name: scene29

Point cloud (view) : 11 MB

View

Sample name: scene8

Point cloud (view) : 11 MB

View


Your browser requires WebGL support in order to properly display the previews.

© 2017 Robotics Group, Jacobs University Bremen.
This website includes software developed and used by the Systems, Robotics and Vision Group, University of the Balearican Islands (srv.uib.es)
based on Bootstrap, Three.js and PapaParse.

Impressum / Imprint