Efficient 3D Object Detection by Fitting Superquadrics to Range Image Data for Robot's Object Manipulation

Biegelbauer, G.; Vincze, Markus

doi:10.1109/robot.2007.363129

Cited by 65 publications

(45 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However the system was tested only on two objects, thus its scalability is not clear. Available models of complex objects are decomposed into superquadric parts in [1,21], and these models are fit to a point cloud. This however needs a database of models, and moreover, their decomposition into superquadric components, which is often difficult to obtain.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction and Verification of 3D Object Models for Grasping

Márton¹,

Goron²,

Rusu³

et al. 2011

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

In this paper we present a method for approximating complete models of objects with 3D shape primitives, by exploiting common symmetries in objects of daily use. Our proposed approach reconstructs boxes and cylindrical parts of objects from sampled point cloud data, and produces CAD-like surface models needed for generating grasping strategies. To verify the results, we present a set of experimental results using real-world data-sets containing a large number of objects from different views.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The two main approaches to produce these representations rely on image or depth information. In the first case, usually a model from a database is matched to the image as in [3,6], while in the latter, a more flexible combination of shape primitives [17], superquadrics [1,21] are fit, or a triangulation of the surface [13,9] is performed.…”

Section: Introductionmentioning

confidence: 99%

Reconstruction and Verification of 3D Object Models for Grasping

Márton¹,

Goron²,

Rusu³

et al. 2011

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…There is a multitude of state-of-the-art approaches based on parameterized superellipsoids for modeling 3D range data with shape primitives. [63][64][65][66] Assuming that an arbitrary point cloud has to be approximated, one SQ is not enough for most objects. The more complex the shape is, the more SQs have to be used to conveniently represent its different parts.…”

Section: Related Workmentioning

confidence: 99%

“…However, good generality is not possible with few parameters for such cases. 64 Besides the advantages of immense parametrization capabilities with at least 11 parameters, intensive research on SQs has also yielded disadvantages in two common strategies for shape approximation. The first strategy is region-growing, starting with a set of hypotheses, the seeds, and let these adapt to the point set.…”

Section: Related Workmentioning

confidence: 99%

“…by point clouds, 90 geometric shape primitives, 62,91,92 or superquadric parametrizations. [63][64][65]69 In our earlier work, 86,93 we have shown that even a box approximation of the point cloud can yield grasp hypotheses, as also interfaces to reason about task, viewpoint, graspability, and more. Our representation efficiently approximates a 3D point cloud by a constellation of Minimum Volume Bounding Boxes (MVBBs).…”

Section: Grasping An Object Based On 3d Shapementioning

confidence: 99%

See 1 more Smart Citation

Towards Grasp-Oriented Visual Perception for Humanoid Robots

Bohg

Barck-Holst

Huebner

et al. 2009

Int. J. Human. Robot.

View full text Add to dashboard Cite

A distinct property of robot vision systems is that they are embodied. Visual information is extracted for the purpose of moving in and interacting with the environment. Thus, different types of perception-action cycles need to be implemented and evaluated.In this paper, we study the problem of designing a vision system for the purpose of object grasping in everyday environments. This vision system is firstly targeted at the interaction with the world through recognition and grasping of objects and secondly at being an interface for the reasoning and planning module to the real world. The latter provides the vision system with a certain task that drives it and defines a specific context, i.e. search for or identify a certain object and analyze it for potential later manipulation. We deal with cases of: (i) known objects, (ii) objects similar to already known objects, and (iii) unknown objects. The perception-action cycle is connected to the reasoning system based on the idea of affordances. All three cases are also related to the state of the art and the terminology in the neuroscientific area.

show abstract

Monocular 3D Object Detection via Feature Domain Adaptation

Liang

Shi

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Efficient 3D Object Detection by Fitting Superquadrics to Range Image Data for Robot's Object Manipulation

Cited by 65 publications

References 23 publications

Reconstruction and Verification of 3D Object Models for Grasping

Reconstruction and Verification of 3D Object Models for Grasping

Towards Grasp-Oriented Visual Perception for Humanoid Robots

Monocular 3D Object Detection via Feature Domain Adaptation

Contact Info

Product

Resources

About