Toward online 3-D object segmentation and mapping
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3193-3200
Abstract
We build on recent fast and accurate 3-D reconstruction techniques to segment objects during scene reconstruction. We take object outline information from change detection to build 3-D models of rigid objects and represent the scene as static and dynamic components. Object models are updated online during mapping, and can integrate segmentation information from sources other than change detection.Keywords
This publication has 14 references indexed in Scilit:
- Deformation-based loop closure for large scale dense RGB-D SLAM2013
- Tracking deformable objects with point clouds2013
- Dense multibody motion estimation and reconstruction from a handheld camera2012
- Exploiting segmentation for robust 3D object matching2012
- RGB-D object discovery via multi-scene analysis2011
- Toward object discovery and modeling via 3-D scene comparison2011
- Motion Segmentation at Any Speed2006
- First contact: an active vision approach to segmentation2004
- Towards object mapping in non-stationary environments with mobile robots2003
- A volumetric method for building complex models from range images1996