Probabilistic 3D object recognition

Ilan Shimshoni; Jean Ponce

doi:10.1023/A:1008172423811

Probabilistic 3D object recognition

Research output: Contribution to journal › Article › peer-review

Abstract

A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing iso-angle and iso-ratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images.

Original language	English
Pages (from-to)	51-70
Number of pages	20
Journal	International Journal of Computer Vision
Volume	36
Issue number	1
DOIs	https://doi.org/10.1023/A:1008172423811
State	Published - 2000
Externally published	Yes

Bibliographical note

Funding Information:
This work was supported in part by the Beckman Institute and the Center for Advanced Study of the University of Illinois at Urbana-Champaign, by the National Science Foundation under grant IRI-9224815, and by the National Aeronautics and Space Administration under grant NAG 1-613.

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1023/A:1008172423811

Cite this

@article{46eb773278054885add6e3d48a22829d,

title = "Probabilistic 3D object recognition",

abstract = "A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing iso-angle and iso-ratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images.",

author = "Ilan Shimshoni and Jean Ponce",

note = "Funding Information: This work was supported in part by the Beckman Institute and the Center for Advanced Study of the University of Illinois at Urbana-Champaign, by the National Science Foundation under grant IRI-9224815, and by the National Aeronautics and Space Administration under grant NAG 1-613.",

year = "2000",

doi = "10.1023/A:1008172423811",

language = "English",

volume = "36",

pages = "51--70",

journal = "International Journal of Computer Vision",

issn = "0920-5691",

publisher = "Springer Netherlands",

number = "1",

}

TY - JOUR

T1 - Probabilistic 3D object recognition

AU - Shimshoni, Ilan

AU - Ponce, Jean

N1 - Funding Information: This work was supported in part by the Beckman Institute and the Center for Advanced Study of the University of Illinois at Urbana-Champaign, by the National Science Foundation under grant IRI-9224815, and by the National Aeronautics and Space Administration under grant NAG 1-613.

PY - 2000

Y1 - 2000

N2 - A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing iso-angle and iso-ratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images.

AB - A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing iso-angle and iso-ratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images.

UR - http://www.scopus.com/inward/record.url?scp=0033871465&partnerID=8YFLogxK

U2 - 10.1023/A:1008172423811

DO - 10.1023/A:1008172423811

M3 - Article

AN - SCOPUS:0033871465

SN - 0920-5691

VL - 36

SP - 51

EP - 70

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

IS - 1

ER -

Probabilistic 3D object recognition

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint