Object part segmentation and classification in range images for grasping

Varadarajan, Karthik Mahesh; Vincze, Markus

doi:10.1109/icar.2011.6088647

Cited by 27 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a common simplification also used in real vision set ups, e.g., by Rosman and Ramamoorthy [23] 2 . We acknowledge that highly sophisticated object segmentation algorithms exist, e.g., [45], [46] and we assume they could be employed to work in a more complex environment, e.g. with real objects and clutter.…”

Section: B the Robotic Perception Systemmentioning

confidence: 99%

Bootstrapping Relational Affordances of Object Pairs Using Transfer

Fichtl

Kraft

Krüger

et al. 2018

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Robots acting in everyday environments need a good knowledge of how a manipulation action can affect pairs of objects in a relationship, such as 'inside' or 'behind' or 'on top'. These relationships afford certain means-end actions such as pulling a container to retrieve the contents, or pulling a tool to retrieve a desired object. We investigate how these relational affordances could be learnt by a robot from its own action experience. A major challenge in this approach is to reduce the number of training samples needed to achieve accuracy, and hence we investigate an approach which can leverage past knowledge to accelerate current learning (which we call bootstrapping). We learn Random Forest based affordance predictors from visual inputs and demonstrate two approaches to knowledge transfer for bootstrapping. In the first approach (direct bootstrapping), the state-space for a new affordance predictor is augmented with the output of previously learnt affordance. In the second approach (category based bootstrapping), we form categories that capture underlying commonalities of a pair of existing affordances and augment the state-space with this category classifier's output. In addition, we introduce a novel heuristic, which suggests how a large set of potential affordance categories can be pruned to leave only those categories which are most promising for bootstrapping future affordances. Our results show that both bootstrapping approaches outperform learning without bootstrapping. We also show that there is no significant difference in performance between direct and category based bootstrapping.

show abstract

Section: B the Robotic Perception Systemmentioning

confidence: 99%

Bootstrapping Relational Affordances of Object Pairs Using Transfer

Fichtl

Kraft

Krüger

et al. 2018

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…Solina and Bajcsy presented a method for recognizing pieces of mail using superquadric parameters estimated from range images. Thus, superquadrics have been used for object shape approximation (Strand et al, 2010;Solina and Bajcsy, 1990;Saito and Kimura, 1996), novelty detection (Drews Jr. et al, 2010), object segmentation (Chevalier et al, 2003;Leonardis et al, 1997), object grasping (Varadarajan and Vincze, 2011), and collision detection (Moustakas et al, 2007).…”

Section: Superquadrics In the Field Of Computer Visionmentioning

confidence: 99%

Primitive Shape Recognition via Superquadric Representation using Large Margin Nearest Neighbor Classifier

Hachiuma

Ozasa

Saitō³

2017

Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

It is known that humans recognize objects using combinations and positional relations of primitive shapes. The first step of such recognition is to recognize 3D primitive shapes. In this paper, we propose a method for primitive shape recognition using superquadric parameters with a metric learning method, large margin nearest neighbor (LMNN). Superquadrics can represent various types of primitive shapes using a single equation with few parameters. These parameters are used as the feature vector of classification. The real objects of primitive shapes are used in our experiment, and the results show the effectiveness of using LMNN for recognition based on superquadrics. Compared to the previous methods, which used k-nearest neighbors (76.5%) and Support Vector Machines (73.5%), our LMNN method has the best performance (79.5%).

show abstract

“…Miller et al (2003) model objects as sets of shape primitives, such as spheres, cylinders, cones or boxes. Varadarajan and Vincze (2011) use the more general Super Quadric Fitting after object part segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…for Superquadric fitting or as a preprocessing module for object recognition by separating one object from a heap of items. • Integrated Path Planning: In the majority of recently published grasping approaches such as Varadarajan and Vincze (2011), grasp planning and path planning are done independently. Grasp points and grasp approach directions are calculated first, computation of inverse kinematic solutions and obstacle avoidance for path planning are done later.…”

Section: Introductionmentioning

confidence: 99%