Time and space efficient pose clustering

Olson,

doi:10.1109/cvpr.1994.323837

Cited by 27 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are numerous approaches for the solution of the pose estimation problem from point correspondences [18,19,22,39,42] or from line correspondences [14,27,33]. Works in automated matching of 3-D with 2-D features include [13,26,28,30,32,36,40,55] whereas in [56] the automated matching is possible when artificial markers are placed in the scene. Finally, Ikeuchi [34] utilizes the reflectance response of the laser range sensor in order to provide an automated solution to the problem.…”

Section: -D Image Registration With Range Datamentioning

confidence: 99%

Geometry and Texture Recovery of Scenes of Large Scale

Stamos

Allen

2002

Computer Vision and Image Understanding

138

View full text Add to dashboard Cite

Section: -D Image Registration With Range Datamentioning

confidence: 99%

Geometry and Texture Recovery of Scenes of Large Scale

Stamos

Allen

2002

Computer Vision and Image Understanding

138

View full text Add to dashboard Cite

“…This general approach to recognition can be traced through many works including [22], [34], work on geometric hashing schemes [35], and on through a collection of excellent recent works [36], [37], [38], [39], [40]. Grimson et al provide a nice general analysis of the problem [41].…”

Section: A Comment About Indexingmentioning

confidence: 99%

How easy is matching 2D line models using local search?

Beveridge

Riseman

1997

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

Abstract-Local search is a well established and highly effective method for solving complex combinatorial optimization problems. Here, local search is adapted to solve difficult geometric matching problems. Matching is posed as the problem of finding the optimal many-to-many correspondence mapping between a line segment model and image line segments. Image data is assumed to be fragmented, noisy, and cluttered. The algorithms presented have been used for robot navigation, photo interpretation, and scene understanding. This paper explores how local search performs as model complexity increases, image clutter increases, and additional model instances are added to the image data. Expected run-times to find optimal matches with 95 percent confidence are determined for 48 distinct problems involving six models. Nonlinear regression is used to estimate run-time growth as a function of problem size. Both polynomial and exponential growth models are fit to the run-time data. For problems with random clutter, the polynomial model fits better and growth is comparable to that for tree search. For problems involving symmetric models and multiple model instances, where tree search is exponential, the polynomial growth model is superior to the exponential growth model for one search algorithm and comparable for another.

show abstract

“…Recent researches in this field have focused on the various components of the recognition problem: which features are invariant and discriminant [6], how it is possible to group features into salient parts [7], how to index models [8], how to identify sets of data feature/model feature pairings consistent with an object, [9] or which similarity measures are relevant [10].…”

Section: Introductionmentioning

confidence: 99%

Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model

Jurie¹

1999

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Time and space efficient pose clustering

Cited by 27 publications

References 13 publications

Geometry and Texture Recovery of Scenes of Large Scale

Geometry and Texture Recovery of Scenes of Large Scale

How easy is matching 2D line models using local search?

Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model

Contact Info

Product

Resources

About