Hierarchical Object Discovery and Dense Modelling from Motion Cues in RGB-D Video
Abstract
In this paper, we propose a novel method for object discovery and dense modelling in RGB-D image sequences using motion cues. We develop our method as a building block for active object perception, such that robots can learn about the environment through perceiving the effects of actions. Our approach simultaneously segments rigid-body motion within key views, and discovers objects and hierarchical relations between object parts. The poses of the key views are optimized in a graph of spatial relations to recover the rigid-body motion trajectories of the camera with respect to the objects. In experiments, we demonstrate that our approach finds moving objects, aligns partial views on the objects, and retrieves hierarchical relations between the objects.
Cite
Text
Stückler and Behnke. "Hierarchical Object Discovery and Dense Modelling from Motion Cues in RGB-D Video." International Joint Conference on Artificial Intelligence, 2013.Markdown
[Stückler and Behnke. "Hierarchical Object Discovery and Dense Modelling from Motion Cues in RGB-D Video." International Joint Conference on Artificial Intelligence, 2013.](https://mlanthology.org/ijcai/2013/stuckler2013ijcai-hierarchical/)BibTeX
@inproceedings{stuckler2013ijcai-hierarchical,
title = {{Hierarchical Object Discovery and Dense Modelling from Motion Cues in RGB-D Video}},
author = {Stückler, Jörg and Behnke, Sven},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2013},
pages = {2502-2509},
url = {https://mlanthology.org/ijcai/2013/stuckler2013ijcai-hierarchical/}
}