A Similarity-Based Aspect-Graph Approach to 3D Object Recognition

Cyr, C.M.; Kimia, Benjamin B.

doi:10.1023/b:visi.0000013088.59081.4c

Cited by 97 publications

(66 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Aspect graphs represent a 3D object as a collection of views of the object [3]. Another approach to build a mixture model for multiple views is to incorporate each view as a single mixture.…”

Section: B Fusionmentioning

confidence: 99%

Sharing landmark information using mixture of Gaussian terrain spatiograms

Lyons

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-In this paper we evaluate the use of a novel spatial histogram called the terrain spatiogram as a common representation for exchanging landmark information between robots working as a team to map an area. Individual robots use range sensors to provide the spatial dimension of the spatiogram and video for the image dimension. We have previously shown that terrain spatiograms can be shared between robots in a heterogeneous team to recognize landmarks and to fuse observations from multiple sensors or multiple platforms.A terrain spatiogram using a mixture of Gaussians (MOG) model is introduced and a corresponding normalized spatiogram similarity measure defined. Two methods to generate a MOG terrain spatiogram are presented and compared experimentally using indoor and outdoor landmark information transferred between two different models of robot equipped with differently configured stereocameras.

show abstract

Section: B Fusionmentioning

confidence: 99%

Sharing landmark information using mixture of Gaussian terrain spatiograms

Lyons

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Then the recognition process can be accomplished by comparison between each model and the graph of the unclassified object. In the work of (Cyr & Kimia, 2004) the similarity between two views of the 3D object is quantified by a metric that measures the distance between their corresponding 2D projected shapes. A slightly different approach is proposed by (Liu et al, 2003), where the so called Directional Histogram Model is defined and evaluated for those objects that have been completely reconstructed.…”

Section: State Of the Art In 3d Recognition Methodsmentioning

confidence: 99%

Experiences in Recognizing Free-Shaped Objects from Partial Views by Using Weighted Cone Curvatures

Cerrada¹,

Salamanca²,

Adán³

et al. 2011

Object Recognition

View full text Add to dashboard Cite

“…Cyr and Kimia [7] presented a similarity-based aspect-graph method, using curve matching and shock matching as the similarity measures between two views, to improve the practicability of aspect-graph representation for extracting the characteristic views. However, the process of updating the aspect-graph representation is inconvenient, since the training views of an object in [7] are sampled at 5-degree increments. To improve the flexibility of the update mechanism, a similarity-based aspect-graph representation that can be constructed with object views sampled at random intervals is studied in this work.…”

Section: Introductionmentioning

confidence: 99%

Shape Memorization and Recognition of 3D Objects Using a Similarity-Based Aspect-Graph Approach

Lin²,

Lin³

et al. 2006

2006 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

This work proposes an incremental combinational algorithm to generate the prototype of a 3D object using 2D images randomly sampled from a viewing sphere. Similarity-based aspect-graph, which contains a set of aspects and prototypes for these aspects, is employed to represent the database of 3D objects. Furthermore, the proposed algorithm is based on low-level features and similarity measures between the features. In this work, the Fourier descriptor and point-to-point lengths are adopted as features, and three similarity measures, called the 1-norm, 2-norm, and K-L distance, are adopted to extract characteristic views. The effectiveness of the proposed algorithm is demonstrated by experiments with an updating mechanism.

show abstract

A Similarity-Based Aspect-Graph Approach to 3D Object Recognition

Cited by 97 publications

References 48 publications

Sharing landmark information using mixture of Gaussian terrain spatiograms

Sharing landmark information using mixture of Gaussian terrain spatiograms

Experiences in Recognizing Free-Shaped Objects from Partial Views by Using Weighted Cone Curvatures

Shape Memorization and Recognition of 3D Objects Using a Similarity-Based Aspect-Graph Approach

Contact Info

Product

Resources

About