Recovery of parametric models from range images: the case for superquadrics with global deformations

Solina, Franc; Bajcsy, Růžena

doi:10.1109/34.44401

Cited by 540 publications

(319 citation statements)

References 20 publications

Supporting

Mentioning

312

Contrasting

Unclassified

Order By: Relevance

“…The ability to recognize objects in 2 1/2-D images such as range scans may also prove valuable in recognizing objects in 2D images when some depth information can be inferred from cues such as shading or motion. Many approaches to 3D object recognition have been put forth, including generalized cylinders [3], superquadrics [7], geons [23], medial axis representations [1], skeletons [4], shape distributions [19], and spherical harmonic representations of global shape [8]. Many of these methods require that the target be segmented from the background, which makes them difficult to apply to realworld 3D scenes.…”

Section: Introductionmentioning

confidence: 99%

Recognizing Objects in Range Data Using Regional Point Descriptors

Frome

Huber

Kolluri

et al. 2004

Lecture Notes in Computer Science

674

494

View full text Add to dashboard Cite

Abstract. Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of these descriptors on the task of recognizing vehicles in range scans of scenes using a database of 56 cars. We compare the two novel descriptors to an existing descriptor, the spin image, showing that the shape context based descriptors have a higher recognition rate on noisy scenes and that 3D shape contexts outperform the others on cluttered scenes.

show abstract

Section: Introductionmentioning

confidence: 99%

Recognizing Objects in Range Data Using Regional Point Descriptors

Frome

Huber

Kolluri

et al. 2004

Lecture Notes in Computer Science

674

494

View full text Add to dashboard Cite

show abstract

“…Popular choices include global models such as generalized splines [3,25], volumetric primitives such as generalized cylinders or superquadrics, e.g. [24]. Alternatively, [9,10,17,21] make use of local parameterizations by fitting a set of local parametric patches to the data.…”

Section: Previous Workmentioning

confidence: 99%

Surface Recovery from 3D Point Data Using a Combined Parametric and Geometric Flow Approach

Savadjiev

Ferrie

Siddiqi

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents a novel method for surface recovery from discrete 3D point data sets. In order to produce improved reconstruction results, the algorithm presented in this paper combines the advantages of a parametric approach to model local surface structure, with the generality and the topological adaptability of a geometric flow approach. This hybrid method is specifically designed to preserve discontinuities in 3D, to be robust to noise, and to reconstruct objects with arbitrary topologies. The key ideas are to tailor a curvature consistency algorithm to the case of a set of points in 3D and to then incorporate a flux maximizing geometric flow for surface reconstruction. The approach is illustrated with experimental results on a variety of data sets. IntroductionSurface reconstruction from incomplete data sets is a classical problem in computer vision. The problem consists of finding a surface S that approximates a physical surface P by using a set of point coordinates sampled from the surface P. These point coordinates may be corrupted with noise, due to imperfections in the acquisition of the data. Like many other problems in computer vision, the problem of surface reconstruction is ill-posed. Prior knowledge about the world and the data acquisition process must therefore be used in order to make it solvable. A good algorithm for surface reconstruction should be robust to noise and result in smooth surfaces, while recovering important structural information from the data, such as edges, ridges and holes. The presence of such structural information in the reconstructed 3D model is very important for further, higher-level processing tasks, such as shape segmentation into parts, object recognition, etc. It should impose as little restrictions on the topology of the reconstructed object as possible. These issues are taken into consideration in the research presented in this paper. The approach to surface reconstruction presented in this article combines two different philosophies, namely that of a parametric reconstruction approach, and that of a geometric flow reconstruction approach. Many algorithms for surface recovery are based on either one of the two types of approaches, but few have attempted to

show abstract

“…Global models, assume a description of the objects into a set of features or parts segment. Common description rely on parametric models [3,19,22], deformable regions [1,4,5], shock graphs [17]... Shape similarity is then measured by comparing location of features and their spatial distributions.…”

Section: Human Body Shape Descriptionmentioning

confidence: 99%

3D Body Reconstruction for Immersive Interaction

Cohen

Lee

2002

Articulated Motion and Deformable Objects

View full text Add to dashboard Cite

Abstract. In this paper we present an approach for capturing 3D body motion and inferring human body posture from detected silhouettes. We show that the integration of two or more silhouettes allows us to perform a 3D body reconstruction while each silhouette can be used for identifying human body postures. The 3D reconstruction is based on the representation of body parts using Generalized Cylinders providing an estimation of the 3D shape of the human body. The 3D shape description is refined by fitting an articulated body model using a particle filter technique. Identifying human body posture from the 2D silhouettes can reduce the complexity of the particle filtering by reducing the search space. We present an appearance-based learning method that uses a shape descriptor of the ¾ silhouette for classifying and identifying human posture. The proposed method does not require an articulated body model fitted onto the reconstructed 3D geometry of the human body: It complements the articulated body model since we can define a mapping between the observed shape and the learned descriptions for inferring the articulated body model.

show abstract

Recovery of parametric models from range images: the case for superquadrics with global deformations

Cited by 540 publications

References 20 publications

Recognizing Objects in Range Data Using Regional Point Descriptors

Recognizing Objects in Range Data Using Regional Point Descriptors

Surface Recovery from 3D Point Data Using a Combined Parametric and Geometric Flow Approach

3D Body Reconstruction for Immersive Interaction

Contact Info

Product

Resources

About