Simultaneous shape recognition and position/orientation detection without image conversion

Julien Agbanhan, Mamoru Minami, Toshiyuki Asakura

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

Abstract

This paper presents a new method of real-time scene recognition for robots, which utilizes a two-dimensional (2-D) gray-scale image of three-dimensional (3-D) objects in the scene, and a genetic algorithm (GA).In the scene recognition process, a model shaping a target object is employed as the knowledge base for recognition purposes. GA is employed for optimization of the evaluation function that expresses the degree of matching between a target beeing imaged and a model shaping the target. Here, the optimization means simultaneous recognition of a target and detection of its position/orientation. Also we are interested here in using GA, since it strikes a good balance between exploration of the search area and exploitation of the results obtained by this search process, without need to scan whole the 2-D image plane. Hence, GA will provide faster recognition performance to the vision system. This GA-based scene recognition method can be designated as "evolutionary scene recognition method", since for every step of the GA's evolution, it struggle to perform the recognition of a target in the new input image of the recognition system. To evaluate the effectiveness of the proposed scene recognition method, experiments are performed and some results are presented.

Original languageEnglish
Title of host publicationProceedings of the 4th Asia-Pacific Conference on Control and Measurement
EditorsS. Chunlin, S. Chunlin
Pages367-372
Number of pages6
Publication statusPublished - 2000
Externally publishedYes
EventProceedings of the 4th Asia-Pacific Conference on Control and Measurement - Guilin, China
Duration: Jul 9 2000Jul 12 2000

Other

OtherProceedings of the 4th Asia-Pacific Conference on Control and Measurement
CountryChina
CityGuilin
Period7/9/007/12/00

Fingerprint

Genetic algorithms
Function evaluation
Robots
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Agbanhan, J., Minami, M., & Asakura, T. (2000). Simultaneous shape recognition and position/orientation detection without image conversion. In S. Chunlin, & S. Chunlin (Eds.), Proceedings of the 4th Asia-Pacific Conference on Control and Measurement (pp. 367-372)

Simultaneous shape recognition and position/orientation detection without image conversion. / Agbanhan, Julien; Minami, Mamoru; Asakura, Toshiyuki.

Proceedings of the 4th Asia-Pacific Conference on Control and Measurement. ed. / S. Chunlin; S. Chunlin. 2000. p. 367-372.

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

Agbanhan, J, Minami, M & Asakura, T 2000, Simultaneous shape recognition and position/orientation detection without image conversion. in S Chunlin & S Chunlin (eds), Proceedings of the 4th Asia-Pacific Conference on Control and Measurement. pp. 367-372, Proceedings of the 4th Asia-Pacific Conference on Control and Measurement, Guilin, China, 7/9/00.
Agbanhan J, Minami M, Asakura T. Simultaneous shape recognition and position/orientation detection without image conversion. In Chunlin S, Chunlin S, editors, Proceedings of the 4th Asia-Pacific Conference on Control and Measurement. 2000. p. 367-372
Agbanhan, Julien ; Minami, Mamoru ; Asakura, Toshiyuki. / Simultaneous shape recognition and position/orientation detection without image conversion. Proceedings of the 4th Asia-Pacific Conference on Control and Measurement. editor / S. Chunlin ; S. Chunlin. 2000. pp. 367-372
@inproceedings{aaa84fa082ab47bf8da03cbc18b710ff,
title = "Simultaneous shape recognition and position/orientation detection without image conversion",
abstract = "This paper presents a new method of real-time scene recognition for robots, which utilizes a two-dimensional (2-D) gray-scale image of three-dimensional (3-D) objects in the scene, and a genetic algorithm (GA).In the scene recognition process, a model shaping a target object is employed as the knowledge base for recognition purposes. GA is employed for optimization of the evaluation function that expresses the degree of matching between a target beeing imaged and a model shaping the target. Here, the optimization means simultaneous recognition of a target and detection of its position/orientation. Also we are interested here in using GA, since it strikes a good balance between exploration of the search area and exploitation of the results obtained by this search process, without need to scan whole the 2-D image plane. Hence, GA will provide faster recognition performance to the vision system. This GA-based scene recognition method can be designated as {"}evolutionary scene recognition method{"}, since for every step of the GA's evolution, it struggle to perform the recognition of a target in the new input image of the recognition system. To evaluate the effectiveness of the proposed scene recognition method, experiments are performed and some results are presented.",
author = "Julien Agbanhan and Mamoru Minami and Toshiyuki Asakura",
year = "2000",
language = "English",
isbn = "7801346955",
pages = "367--372",
editor = "S. Chunlin and S. Chunlin",
booktitle = "Proceedings of the 4th Asia-Pacific Conference on Control and Measurement",

}

TY - GEN

T1 - Simultaneous shape recognition and position/orientation detection without image conversion

AU - Agbanhan, Julien

AU - Minami, Mamoru

AU - Asakura, Toshiyuki

PY - 2000

Y1 - 2000

N2 - This paper presents a new method of real-time scene recognition for robots, which utilizes a two-dimensional (2-D) gray-scale image of three-dimensional (3-D) objects in the scene, and a genetic algorithm (GA).In the scene recognition process, a model shaping a target object is employed as the knowledge base for recognition purposes. GA is employed for optimization of the evaluation function that expresses the degree of matching between a target beeing imaged and a model shaping the target. Here, the optimization means simultaneous recognition of a target and detection of its position/orientation. Also we are interested here in using GA, since it strikes a good balance between exploration of the search area and exploitation of the results obtained by this search process, without need to scan whole the 2-D image plane. Hence, GA will provide faster recognition performance to the vision system. This GA-based scene recognition method can be designated as "evolutionary scene recognition method", since for every step of the GA's evolution, it struggle to perform the recognition of a target in the new input image of the recognition system. To evaluate the effectiveness of the proposed scene recognition method, experiments are performed and some results are presented.

AB - This paper presents a new method of real-time scene recognition for robots, which utilizes a two-dimensional (2-D) gray-scale image of three-dimensional (3-D) objects in the scene, and a genetic algorithm (GA).In the scene recognition process, a model shaping a target object is employed as the knowledge base for recognition purposes. GA is employed for optimization of the evaluation function that expresses the degree of matching between a target beeing imaged and a model shaping the target. Here, the optimization means simultaneous recognition of a target and detection of its position/orientation. Also we are interested here in using GA, since it strikes a good balance between exploration of the search area and exploitation of the results obtained by this search process, without need to scan whole the 2-D image plane. Hence, GA will provide faster recognition performance to the vision system. This GA-based scene recognition method can be designated as "evolutionary scene recognition method", since for every step of the GA's evolution, it struggle to perform the recognition of a target in the new input image of the recognition system. To evaluate the effectiveness of the proposed scene recognition method, experiments are performed and some results are presented.

UR - http://www.scopus.com/inward/record.url?scp=0034590565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034590565&partnerID=8YFLogxK

M3 - Conference contribution

SN - 7801346955

SP - 367

EP - 372

BT - Proceedings of the 4th Asia-Pacific Conference on Control and Measurement

A2 - Chunlin, S.

A2 - Chunlin, S.

ER -