An Efficient Motion Segmentation Algorithm for Multibody RGB-D SLAM

Publisher:
Australian Robotics and Automation Association
Publication Type:
Conference Proceeding
Citation:
Proceedings of Australasian Conference on Robotics and Automation, 2013, pp. 1 - 10
Issue Date:
2013-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2012008484OK.pdf4.12 MB
Adobe PDF
A simple motion segmentation algorithm using only two frames of RGB-D data is proposed, and both simulation and experimental segmentation results show its efficiency and reliability. To further verify its usability in multibody SLAM scenarios, we firstly apply it to a simulated typical multibody SLAM problem with only a RGB-D camera, and then utilize it to segment a real RGB-D dataset collected by ourselves. Based on the good results of our motion segmentation algorithm, we can get satisfactory SLAM results for the simulated problem and the segmentation results using real data also enable us to get visual odometry for each motion group thus facilitate the following steps to solve the practical multibody RGB-D SLAM problems.
Please use this identifier to cite or link to this item: