Universität Bonn: Autonomous Intelligent SystemsInstitute for Computer Science VI: Autonomous Intelligent Systems

Kinect segmentation dataset

Description: 

The dataset consists of 30 XYZRGB point clouds with manually annotated ground truth for plane and cylinder segmentation. The images have been obtained indoors with a Microsoft Kinect camera. The image resolution is 640x480. The point clouds are given in the pcd file format which can be read using the PCL library. The ground truth is compatible to the SegComp evaluation tool.

Download: 

You can download the datasets [here] (zip archive, 48MB) and [here] (zip archive, 50MB) .

If you refer to our dataset, please cite:

Bastian Oehler, Joerg Stueckler, Jochen Welle, Dirk Schulz, and Sven Behnke. "Efficient Multi-Resolution Plane Segmentation of 3D Point Clouds" Proceedings of the 4th International Conference on Intelligent Robotics and Applications (ICIRA), Aachen, December 2011




Last updated: December 16, 2011 by Joerg Stueckler (stueckler _at_ ais.uni-bonn.de)

University of Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI