Grasping surfaces of revolution: Simultaneous pose and shape recovery from two views

Phillips, Cody; Lecce, Matthieu; Davis, Casey W.; Daniilidis, Kostas

doi:10.1109/icra.2015.7139366

Cited by 6 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Solving for symmetry correspondence has been tried for surfaces of revolution, which are characterized by rotational symmetry [21][22][23] as well as for mirror-symmetrical polyhedral objects, where edge features are compared with respect to 2-D affine similarities (Refs. [24][25][26].…”

Section: Related Researchmentioning

confidence: 99%

Figure-ground organization based on three-dimensional symmetry

Michaux

Jayadevan

Delp

et al. 2016

J. Electron. Imaging

View full text Add to dashboard Cite

Abstract. We present an approach to figure/ground organization using mirror symmetry as a general purpose and biologically motivated prior. Psychophysical evidence suggests that the human visual system makes use of symmetry in producing three-dimensional (3-D) percepts of objects. 3-D symmetry aids in scene organization because (i) almost all objects exhibit symmetry, and (ii) configurations of objects are not likely to be symmetric unless they share some additional relationship. No general purpose approach is known for solving 3-D symmetry correspondence in two-dimensional (2-D) camera images, because few invariants exist. Therefore, we present a general purpose method for finding 3-D symmetry correspondence by pairing the problem with the two-view geometry of the binocular correspondence problem. Mirror symmetry is a spatially global property that is not likely to be lost in the spatially local noise of binocular depth maps. We tested our approach on a corpus of 180 images collected indoors with a stereo camera system. K -means clustering was used as a baseline for comparison. The informative nature of the symmetry prior makes it possible to cluster data without a priori knowledge of which objects may appear in the scene, and without knowing how many objects there are in the scene. IntroductionAccording to most studies of human vision, the first step in visual perception is determining whether there are objects in front of the observer: where they are and how many there are. This step (visual function) is called figure-ground organization (FGO). 1 The computer vision community refers to this problem as object discovery. As with all natural visual functions of human observers, FGO operates in three-dimensional (3-D) space, as opposed to the two-dimensional (2-D) retinal image. It follows that it is natural to think about visual mechanisms underlying FGO as based on 3-D operations. However, the fact that the input to the visual system is one or more 2-D retinal images encouraged previous researchers to look for a theory of FGO based on 2-D operations. This is how the human vision community studied FGO. Consider the prototypical example of Edgar Rubin's vase-faces stimulus.2 In this 2-D stimulus, there are two possible interpretations depending on which region is perceived as a "figure" as opposed to the "ground." Similar bistable stimuli have been used during the last several dozen years of FGO research in human vision.3,4 This research provided a large body of results, but few theories and computational models. Furthermore, the proposed models are usually not suitable for real retinal or camera images representing 3-D scenes. This paper breaks with this tradition and looks for 3-D operations that can establish the correct 3-D FGO.

show abstract

Section: Related Researchmentioning

confidence: 99%

Figure-ground organization based on three-dimensional symmetry

Michaux

Jayadevan

Delp

et al. 2016

J. Electron. Imaging

View full text Add to dashboard Cite

show abstract

“…Closest to this work are approaches on SOR reconstruction and pose estimation, using two views and manually segmented contours [23], or automatically segmenting contours in a single view before applying reconstruction [3]. The goal of this work is to jointly segment and reconstruct the object in an effort to achieve more robustness.…”

Section: Related Workmentioning

confidence: 99%

“…The apparent contour was automatically annotated by rendering the contours of the object's 3D model in the image. The 3D model of each object was obtained by spray-painting it, manually segmenting its apparent contour in multiple views and applying the reconstruction process described in [23], which is exact when the object pose in the camera frame is known.…”

Section: ) Annotated Dataset For Transparent Edge Detectionmentioning

confidence: 99%

“…As described in [27], [5], [23], the cross-sections (visible coaxial circles) of the SOR are projected to ellipses and are view-independent, whereas points on the occluding curve Γ are projected to an apparent contour γ that is view-dependent. Indeed, the 3D curve Γ is view-dependent since changing position of the camera center with respect to the object also changes the locus of points where camera rays are tangent to the object.…”

Section: B Generating Transparent Sor Hypothesesmentioning

confidence: 99%

“…The small-size dynamic program takes a finds an optimal smooth symmetric curve with high edge response and symmetric edge orientations. The curve and the 3D axis are used to perform single-view SOR reconstruction with known pose, as described in previous work [5], [23]. The construction used in this step is the one from [23], and leverages the fact that for a point X at height h and radius r on the occluding curve Γ and its corresponding image point x ∈ γ, the imaged cross-section at height h and radius r (appearing as an ellipse in the image) is tangent to γ at x, as shown in Fig.…”

Section: B Generating Transparent Sor Hypothesesmentioning

confidence: 99%

See 2 more Smart Citations

Seeing Glassware: from Edge Detection to Pose Estimation and Shape Recovery

Phillips¹,

Lecce²,

Daniilidis³

Robotics: Science and Systems XII

Self Cite

View full text Add to dashboard Cite

Abstract-Perception of transparent objects has been an open challenge in robotics despite advances in sensors and datadriven learning approaches. In this paper, we introduce a new approach that combines recent advances in learnt object detectors with perceptual grouping in 2D, and projective geometry of apparent contours in 3D. We train a state of the art structured edge detector on an annotated set of foreground glassware. We assume that we deal with surfaces of revolution (SOR) and apply perceptual symmetry grouping in a 2D spherical transformation of the image to obtain a 2D detection of the glassware object and a hypothesis about its 2D axis. Rather than stopping at a single view detection, we ultimately want to reconstruct the 3D shape of the object and its 3D pose to allow for a robot to grasp it. Using two views allows us to decouple the 3D axis localization from the shape estimation. We develop a parametrization that uniquely relates the shape reconstruction of SOR to given a set of contour points and tangents. Finally, we provide the first annotated dataset for 2D detection, 3D pose and 3D shape of glassware and we show results comparable to category-based detection and localization of opaque objects without any training on the object shape.

show abstract

Reconstruction of 3D Pose for Surfaces of Revolution from Range Data

Pavlakos

Daniilidis

2015

2015 International Conference on 3D Vision

View full text Add to dashboard Cite

Grasping surfaces of revolution: Simultaneous pose and shape recovery from two views

Cited by 6 publications

References 18 publications

Figure-ground organization based on three-dimensional symmetry

Figure-ground organization based on three-dimensional symmetry

Seeing Glassware: from Edge Detection to Pose Estimation and Shape Recovery

Reconstruction of 3D Pose for Surfaces of Revolution from Range Data

Contact Info

Product

Resources

About