Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle

Khin Nwe Lwin, Kenta Yonemori, Myo Myint, Mukada Naoki, Mamoru Minami, Akira Yanou, Takayuki Matsuno

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

1 Citation (Scopus)

Abstract

Genetic algorithm (GA) has been applied for real-time pose estimation in this research because of its simplicity, global perspective and repeatable ability. In many of these different situations or problems, optimum selection parameters are a critical factors in the performance of GA. We have developed visual-servo type underwater vehicle using dual-eye camera and 3D marker using real-time pose tracking, named as Real-time Multi-step GA. The relative pose between a vehicle and a 3D-marker can be estimated by Model-based matching method. To recognize the pose of the marker with respect to the vehicle, it is needed to utilize the optimum searching in real-time, and the real-time pose estimation problem can be converted into an optimization problem over a time-varying distribution function with multiple variables. Therefore, analyses the convergence performance of real-time multi-step GA for 3D model-based recognition for underwater vehicle was conducted and reported in this paper. The main aim of this paper is to choose the best parameters for GA that are optimized over population size, selection rate, mutation rate based on their relative fitness value to improve the performance of searching in time domain. The experimental results show that the proposed system effectively improved the searching performance of Real-time multi-step GA for real time pose tracking, having enable an automatic docking of underwater vehicle by dual-eyes visual servoing.

Original languageEnglish
Title of host publicationTechno-Ocean 2016: Return to the Oceans
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages519-526
Number of pages8
ISBN (Electronic)9781509024452
DOIs
Publication statusPublished - Mar 30 2017
Event16th Techno-Ocean, Techno-Ocean 2016 - Kobe, Japan
Duration: Oct 6 2016Oct 8 2016

Other

Other16th Techno-Ocean, Techno-Ocean 2016
CountryJapan
CityKobe
Period10/6/1610/8/16

Fingerprint

underwater vehicles
underwater vehicle
Visual servoing
genetic algorithms
genetic algorithm
Genetic algorithms
optimization
markers
vehicles
size selection
global perspective
Distribution functions
Cameras
fitness
population size
mutation
mutations
distribution functions
cameras

Keywords

  • Performance analysis
  • Real-time Multi-step GA
  • Underwater vehicle
  • Visual-servoing

ASJC Scopus subject areas

  • Oceanography
  • Water Science and Technology
  • Energy Engineering and Power Technology
  • Ocean Engineering
  • Instrumentation

Cite this

Lwin, K. N., Yonemori, K., Myint, M., Naoki, M., Minami, M., Yanou, A., & Matsuno, T. (2017). Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle. In Techno-Ocean 2016: Return to the Oceans (pp. 519-526). [7890709] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/Techno-Ocean.2016.7890709

Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle. / Lwin, Khin Nwe; Yonemori, Kenta; Myint, Myo; Naoki, Mukada; Minami, Mamoru; Yanou, Akira; Matsuno, Takayuki.

Techno-Ocean 2016: Return to the Oceans. Institute of Electrical and Electronics Engineers Inc., 2017. p. 519-526 7890709.

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

Lwin, KN, Yonemori, K, Myint, M, Naoki, M, Minami, M, Yanou, A & Matsuno, T 2017, Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle. in Techno-Ocean 2016: Return to the Oceans., 7890709, Institute of Electrical and Electronics Engineers Inc., pp. 519-526, 16th Techno-Ocean, Techno-Ocean 2016, Kobe, Japan, 10/6/16. https://doi.org/10.1109/Techno-Ocean.2016.7890709
Lwin KN, Yonemori K, Myint M, Naoki M, Minami M, Yanou A et al. Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle. In Techno-Ocean 2016: Return to the Oceans. Institute of Electrical and Electronics Engineers Inc. 2017. p. 519-526. 7890709 https://doi.org/10.1109/Techno-Ocean.2016.7890709
Lwin, Khin Nwe ; Yonemori, Kenta ; Myint, Myo ; Naoki, Mukada ; Minami, Mamoru ; Yanou, Akira ; Matsuno, Takayuki. / Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle. Techno-Ocean 2016: Return to the Oceans. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 519-526
@inproceedings{43151335df434394bad7169101753468,
title = "Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle",
abstract = "Genetic algorithm (GA) has been applied for real-time pose estimation in this research because of its simplicity, global perspective and repeatable ability. In many of these different situations or problems, optimum selection parameters are a critical factors in the performance of GA. We have developed visual-servo type underwater vehicle using dual-eye camera and 3D marker using real-time pose tracking, named as Real-time Multi-step GA. The relative pose between a vehicle and a 3D-marker can be estimated by Model-based matching method. To recognize the pose of the marker with respect to the vehicle, it is needed to utilize the optimum searching in real-time, and the real-time pose estimation problem can be converted into an optimization problem over a time-varying distribution function with multiple variables. Therefore, analyses the convergence performance of real-time multi-step GA for 3D model-based recognition for underwater vehicle was conducted and reported in this paper. The main aim of this paper is to choose the best parameters for GA that are optimized over population size, selection rate, mutation rate based on their relative fitness value to improve the performance of searching in time domain. The experimental results show that the proposed system effectively improved the searching performance of Real-time multi-step GA for real time pose tracking, having enable an automatic docking of underwater vehicle by dual-eyes visual servoing.",
keywords = "Performance analysis, Real-time Multi-step GA, Underwater vehicle, Visual-servoing",
author = "Lwin, {Khin Nwe} and Kenta Yonemori and Myo Myint and Mukada Naoki and Mamoru Minami and Akira Yanou and Takayuki Matsuno",
year = "2017",
month = "3",
day = "30",
doi = "10.1109/Techno-Ocean.2016.7890709",
language = "English",
pages = "519--526",
booktitle = "Techno-Ocean 2016: Return to the Oceans",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Performance analyses and optimization of Real-time Multi-step GA for visual-servoing based underwater vehicle

AU - Lwin, Khin Nwe

AU - Yonemori, Kenta

AU - Myint, Myo

AU - Naoki, Mukada

AU - Minami, Mamoru

AU - Yanou, Akira

AU - Matsuno, Takayuki

PY - 2017/3/30

Y1 - 2017/3/30

N2 - Genetic algorithm (GA) has been applied for real-time pose estimation in this research because of its simplicity, global perspective and repeatable ability. In many of these different situations or problems, optimum selection parameters are a critical factors in the performance of GA. We have developed visual-servo type underwater vehicle using dual-eye camera and 3D marker using real-time pose tracking, named as Real-time Multi-step GA. The relative pose between a vehicle and a 3D-marker can be estimated by Model-based matching method. To recognize the pose of the marker with respect to the vehicle, it is needed to utilize the optimum searching in real-time, and the real-time pose estimation problem can be converted into an optimization problem over a time-varying distribution function with multiple variables. Therefore, analyses the convergence performance of real-time multi-step GA for 3D model-based recognition for underwater vehicle was conducted and reported in this paper. The main aim of this paper is to choose the best parameters for GA that are optimized over population size, selection rate, mutation rate based on their relative fitness value to improve the performance of searching in time domain. The experimental results show that the proposed system effectively improved the searching performance of Real-time multi-step GA for real time pose tracking, having enable an automatic docking of underwater vehicle by dual-eyes visual servoing.

AB - Genetic algorithm (GA) has been applied for real-time pose estimation in this research because of its simplicity, global perspective and repeatable ability. In many of these different situations or problems, optimum selection parameters are a critical factors in the performance of GA. We have developed visual-servo type underwater vehicle using dual-eye camera and 3D marker using real-time pose tracking, named as Real-time Multi-step GA. The relative pose between a vehicle and a 3D-marker can be estimated by Model-based matching method. To recognize the pose of the marker with respect to the vehicle, it is needed to utilize the optimum searching in real-time, and the real-time pose estimation problem can be converted into an optimization problem over a time-varying distribution function with multiple variables. Therefore, analyses the convergence performance of real-time multi-step GA for 3D model-based recognition for underwater vehicle was conducted and reported in this paper. The main aim of this paper is to choose the best parameters for GA that are optimized over population size, selection rate, mutation rate based on their relative fitness value to improve the performance of searching in time domain. The experimental results show that the proposed system effectively improved the searching performance of Real-time multi-step GA for real time pose tracking, having enable an automatic docking of underwater vehicle by dual-eyes visual servoing.

KW - Performance analysis

KW - Real-time Multi-step GA

KW - Underwater vehicle

KW - Visual-servoing

UR - http://www.scopus.com/inward/record.url?scp=85018350631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018350631&partnerID=8YFLogxK

U2 - 10.1109/Techno-Ocean.2016.7890709

DO - 10.1109/Techno-Ocean.2016.7890709

M3 - Conference contribution

AN - SCOPUS:85018350631

SP - 519

EP - 526

BT - Techno-Ocean 2016: Return to the Oceans

PB - Institute of Electrical and Electronics Engineers Inc.

ER -