Obtaining polyhedral model by integration of multiview images via genetic algorithms

Hideo Saito, Satoshi Kirihara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Shape modeling is a very important issue for many study, for example, object recognition for robot vision, virtual environment construction, and so on. In this paper, a new method for obtaining polyhedral model from multiview images using genetic algorithms (GAs) is proposed. In this method, a similarity between model and every input image is calculated, and then the model which has the maximum similarity is found. For finding the model of maximum similarity, genetic algorithms are used as the optimization method. In the genetic algorithm, the sharing scheme is employed for efficient detection of multiple solution, because some shape may be represented by multiple shape models. Some results of modeling experiments from real multiple images demonstrate that the proposed method can robustly generate model by using the GA.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Pages174-184
Number of pages11
Volume3204
DOIs
Publication statusPublished - 1997
EventThree-Dimensional Imaging and Laser-based Systems for Metrology and Inspection III - Pittsburgh, PA, United States
Duration: 1997 Oct 141997 Oct 14

Other

OtherThree-Dimensional Imaging and Laser-based Systems for Metrology and Inspection III
CountryUnited States
CityPittsburgh, PA
Period97/10/1497/10/14

Fingerprint

genetic algorithms
Genetic algorithms
Genetic Algorithm
Model
Robot Vision
Shape Modeling
Object recognition
Multiple Solutions
Object Recognition
Virtual Environments
robots
Virtual reality
Computer vision
Optimization Methods
Sharing
optimization
Modeling
Demonstrate
Experiment
Similarity

Keywords

  • Computer vision
  • Genetic algorithms
  • Multiview images
  • Polyhedral
  • Shape modeling

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Saito, H., & Kirihara, S. (1997). Obtaining polyhedral model by integration of multiview images via genetic algorithms. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3204, pp. 174-184) https://doi.org/10.1117/12.294456

Obtaining polyhedral model by integration of multiview images via genetic algorithms. / Saito, Hideo; Kirihara, Satoshi.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3204 1997. p. 174-184.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Saito, H & Kirihara, S 1997, Obtaining polyhedral model by integration of multiview images via genetic algorithms. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 3204, pp. 174-184, Three-Dimensional Imaging and Laser-based Systems for Metrology and Inspection III, Pittsburgh, PA, United States, 97/10/14. https://doi.org/10.1117/12.294456
Saito H, Kirihara S. Obtaining polyhedral model by integration of multiview images via genetic algorithms. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3204. 1997. p. 174-184 https://doi.org/10.1117/12.294456
Saito, Hideo ; Kirihara, Satoshi. / Obtaining polyhedral model by integration of multiview images via genetic algorithms. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3204 1997. pp. 174-184
@inproceedings{fdf403a3391f433185f8ad8623e746d8,
title = "Obtaining polyhedral model by integration of multiview images via genetic algorithms",
abstract = "Shape modeling is a very important issue for many study, for example, object recognition for robot vision, virtual environment construction, and so on. In this paper, a new method for obtaining polyhedral model from multiview images using genetic algorithms (GAs) is proposed. In this method, a similarity between model and every input image is calculated, and then the model which has the maximum similarity is found. For finding the model of maximum similarity, genetic algorithms are used as the optimization method. In the genetic algorithm, the sharing scheme is employed for efficient detection of multiple solution, because some shape may be represented by multiple shape models. Some results of modeling experiments from real multiple images demonstrate that the proposed method can robustly generate model by using the GA.",
keywords = "Computer vision, Genetic algorithms, Multiview images, Polyhedral, Shape modeling",
author = "Hideo Saito and Satoshi Kirihara",
year = "1997",
doi = "10.1117/12.294456",
language = "English",
volume = "3204",
pages = "174--184",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Obtaining polyhedral model by integration of multiview images via genetic algorithms

AU - Saito, Hideo

AU - Kirihara, Satoshi

PY - 1997

Y1 - 1997

N2 - Shape modeling is a very important issue for many study, for example, object recognition for robot vision, virtual environment construction, and so on. In this paper, a new method for obtaining polyhedral model from multiview images using genetic algorithms (GAs) is proposed. In this method, a similarity between model and every input image is calculated, and then the model which has the maximum similarity is found. For finding the model of maximum similarity, genetic algorithms are used as the optimization method. In the genetic algorithm, the sharing scheme is employed for efficient detection of multiple solution, because some shape may be represented by multiple shape models. Some results of modeling experiments from real multiple images demonstrate that the proposed method can robustly generate model by using the GA.

AB - Shape modeling is a very important issue for many study, for example, object recognition for robot vision, virtual environment construction, and so on. In this paper, a new method for obtaining polyhedral model from multiview images using genetic algorithms (GAs) is proposed. In this method, a similarity between model and every input image is calculated, and then the model which has the maximum similarity is found. For finding the model of maximum similarity, genetic algorithms are used as the optimization method. In the genetic algorithm, the sharing scheme is employed for efficient detection of multiple solution, because some shape may be represented by multiple shape models. Some results of modeling experiments from real multiple images demonstrate that the proposed method can robustly generate model by using the GA.

KW - Computer vision

KW - Genetic algorithms

KW - Multiview images

KW - Polyhedral

KW - Shape modeling

UR - http://www.scopus.com/inward/record.url?scp=57649200150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649200150&partnerID=8YFLogxK

U2 - 10.1117/12.294456

DO - 10.1117/12.294456

M3 - Conference contribution

AN - SCOPUS:57649200150

VL - 3204

SP - 174

EP - 184

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -