Grasping novel objects with depth segmentation

Rao, D. N.; Le, Quoc V.; Phoka, Thanathorn; Quigley, Morgan; Sudsang, Attawith; Ng, Andrew Y.

doi:10.1109/iros.2010.5650493

Cited by 110 publications

(85 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For each image of every dataset, objects have been manually labelled by delineating the pixels inside the object boundary. If the segmented objects overlap more than 70% with the corresponding object pixels, we consider the object as successfully segmented, as in [15].…”

Section: Resultsmentioning

confidence: 99%

“…Comparison between different approaches. First and second row: original images; third row: [5]; fourth row: [4]; fifth row: [15]; sixth and seventh row: our approach.…”

Section: Discussionmentioning

confidence: 99%

“…The algorithm does not explicitly deal with missing depth information in computing the border ownership. In [15] the authors extend a graph-based segmentation algorithm [5] by integrating depth as a fourth component among RGB components in computing difference between adjacent pixels.…”

mentioning

confidence: 99%

“…The contribution of this work is the extension of a fast graph-based segmentation algorithm [5] with the inclusion of depth information (similarly to [15]) and saliency.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Fast Graph-Based Object Segmentation for RGB-D Images

Toscana

Rosa

2017

Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016

View full text Add to dashboard Cite

Abstract-Object segmentation is an important capability for robotic systems, in particular for grasping. We present a graphbased approach for the segmentation of simple objects from RGB-D images. We are interested in segmenting objects with large variety in appearance, from lack of texture to strong textures, for the task of robotic grasping. The algorithm does not rely on image features or machine learning. We propose a modified Canny edge detector for extracting robust edges by using depth information and two simple cost functions for combining color and depth cues. The cost functions are used to build an undirected graph, which is partitioned using the concept of internal and external differences between graph regions. The partitioning is fast with O(N logN ) complexity. We also discuss ways to deal with missing depth information. We test the approach on different publicly available RGB-D object datasets, such as the Rutgers APC RGB-D dataset and the RGB-D Object Dataset, and compare the results with other existing methods.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Comparison between different approaches. First and second row: original images; third row: [5]; fourth row: [4]; fifth row: [15]; sixth and seventh row: our approach.…”

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

“…The contribution of this work is the extension of a fast graph-based segmentation algorithm [5] with the inclusion of depth information (similarly to [15]) and saliency.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Fast Graph-Based Object Segmentation for RGB-D Images

Toscana

Rosa

2017

Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016

View full text Add to dashboard Cite

show abstract

“…These sensors have contributed to a wealth of research in a variety of domains including autonomous driving [17], 3D modelling [12], grasping and manipulation [21], [13] and object recognition [11], to only mention a few. The work presented here belongs to this overall effort attempting to exploit the richness of 3D data to build more accurate perception systems.…”

Section: Introductionmentioning

confidence: 99%

Scan segments matching for pairwise 3D alignment

Douillard

Quadros

Morton

et al. 2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-This paper presents a method for pairwise 3D alignment which solves data association by matching scan segments across scans. Generating accurate segment associations allows to run a modified version of the Iterative Closest Point (ICP) algorithm where the search for point-to-point correspondences is constrained to associated segments. The novelty of the proposed approach is in the segment matching process which takes into account the proximity of segments, their shape, and the consistency of their relative locations in each scan. Scan segmentation is here assumed to be given (recent studies provide various alternatives [10], [19]). The method is tested on seven sequences of Velodyne scans acquired in urban environments. Unlike various other standard versions of ICP, which fail to recover correct alignment when the displacement between scans increases, the proposed method is shown to be robust to displacements of several meters. In addition, it is shown to lead to savings in computational times which are potentially critical in real-time applications.

show abstract