Abstract
In this chapter, the 6D pose estimation problem is solved using depth maps. Depth maps contain 3D scanner data but saved in a 2D image. This allows for very efficient scene analysis. An approach is described how grasp poses on unknown objects can be computed in real-time allowing for near time optimal grasping. It is further described how the approach can be extended for bin-picking tasks of known objects by combining the visual scene analysis with inertial feature analysis. Experiments close the chapter.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Precise object poses are needed, in cases where objects are only allowed to be grasped at predefined regions.
- 2.
Not considering ambiguities arising from symmetry.
- 3.
- 4.
Grasps in which the gripper is closed to grasp are called outer grasps, grasps in which the gripper is opened to grasp are called inner grasps.
- 5.
Inertia Measurement Unit.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Buchholz, D. (2016). Depth Map Based Pose Estimation. In: Bin-Picking. Studies in Systems, Decision and Control, vol 44. Springer, Cham. https://doi.org/10.1007/978-3-319-26500-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-26500-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26498-1
Online ISBN: 978-3-319-26500-1
eBook Packages: EngineeringEngineering (R0)