Verification of photo-model-based pose estimation and handling of unique clothes under illumination varieties

Khaing Win Phyu, Ryuki Funakubo, Ryota Hagiwara, Hongzhi Tian, Mamoru Minami

Research output: Contribution to journalArticle

Abstract

Human can recognize and handle (pick and place) easily the objects with a variety of different shapes, colors, sizes, and humans’ eyes are adaptable to various light environments with a certain tolerance. However, it is difficult for robots to recognize deformable objects such as cloth, string, etc., especially if an object is unique. Additionally, there have been difficulties for robots with vision sensors (cameras) to accurately detect and handle objects under various light environments. This paper proposes a cloth handling system that recognizes an unique cloth appeared in front of a robot by a photo-model-based approach. The photo-model-based approach has been adopted since the photo-model can be made at once by taking a photo of the unique cloth. In proposed cloths’ pose estimation method, a photo-model projected from 3D to 2D is used, where this system does not need defining the object’s size, shape, design, color and weight. It detects the cloth through model-based matching method and Genetic Algorithm (GA). The handling performance by the proposed method with dual-eyes cameras has been verified, revealing that the proposed system has leeway to recognize and handle the unique cloth in lighting varieties from 100 lx to 1300 lx. In addition, 3D recognition and handling accuracy have been confirmed to be practically effective by conducting the recognition/handling experiments under different light conditions.

Original languageEnglish
JournalJournal of Advanced Mechanical Design, Systems and Manufacturing
Volume12
Issue number2
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Lighting
Robots
Cameras
Color
Genetic algorithms
Sensors
Experiments

Keywords

  • Dual-eyes cameras
  • Genetic Algorithm
  • Handling
  • Illumination
  • Photo-model-based cloth recognition
  • Visual servoing

ASJC Scopus subject areas

  • Mechanical Engineering
  • Industrial and Manufacturing Engineering

Cite this

Verification of photo-model-based pose estimation and handling of unique clothes under illumination varieties. / Phyu, Khaing Win; Funakubo, Ryuki; Hagiwara, Ryota; Tian, Hongzhi; Minami, Mamoru.

In: Journal of Advanced Mechanical Design, Systems and Manufacturing, Vol. 12, No. 2, 01.01.2018.

Research output: Contribution to journalArticle

@article{80494a79526042d9a9912798ddbe8c01,
title = "Verification of photo-model-based pose estimation and handling of unique clothes under illumination varieties",
abstract = "Human can recognize and handle (pick and place) easily the objects with a variety of different shapes, colors, sizes, and humans’ eyes are adaptable to various light environments with a certain tolerance. However, it is difficult for robots to recognize deformable objects such as cloth, string, etc., especially if an object is unique. Additionally, there have been difficulties for robots with vision sensors (cameras) to accurately detect and handle objects under various light environments. This paper proposes a cloth handling system that recognizes an unique cloth appeared in front of a robot by a photo-model-based approach. The photo-model-based approach has been adopted since the photo-model can be made at once by taking a photo of the unique cloth. In proposed cloths’ pose estimation method, a photo-model projected from 3D to 2D is used, where this system does not need defining the object’s size, shape, design, color and weight. It detects the cloth through model-based matching method and Genetic Algorithm (GA). The handling performance by the proposed method with dual-eyes cameras has been verified, revealing that the proposed system has leeway to recognize and handle the unique cloth in lighting varieties from 100 lx to 1300 lx. In addition, 3D recognition and handling accuracy have been confirmed to be practically effective by conducting the recognition/handling experiments under different light conditions.",
keywords = "Dual-eyes cameras, Genetic Algorithm, Handling, Illumination, Photo-model-based cloth recognition, Visual servoing",
author = "Phyu, {Khaing Win} and Ryuki Funakubo and Ryota Hagiwara and Hongzhi Tian and Mamoru Minami",
year = "2018",
month = "1",
day = "1",
doi = "10.1299/jamdsm.2018jamdsm0047",
language = "English",
volume = "12",
journal = "Journal of Advanced Mechanical Design, Systems and Manufacturing",
issn = "1881-3054",
publisher = "Japan Society of Mechanical Engineers",
number = "2",

}

TY - JOUR

T1 - Verification of photo-model-based pose estimation and handling of unique clothes under illumination varieties

AU - Phyu, Khaing Win

AU - Funakubo, Ryuki

AU - Hagiwara, Ryota

AU - Tian, Hongzhi

AU - Minami, Mamoru

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Human can recognize and handle (pick and place) easily the objects with a variety of different shapes, colors, sizes, and humans’ eyes are adaptable to various light environments with a certain tolerance. However, it is difficult for robots to recognize deformable objects such as cloth, string, etc., especially if an object is unique. Additionally, there have been difficulties for robots with vision sensors (cameras) to accurately detect and handle objects under various light environments. This paper proposes a cloth handling system that recognizes an unique cloth appeared in front of a robot by a photo-model-based approach. The photo-model-based approach has been adopted since the photo-model can be made at once by taking a photo of the unique cloth. In proposed cloths’ pose estimation method, a photo-model projected from 3D to 2D is used, where this system does not need defining the object’s size, shape, design, color and weight. It detects the cloth through model-based matching method and Genetic Algorithm (GA). The handling performance by the proposed method with dual-eyes cameras has been verified, revealing that the proposed system has leeway to recognize and handle the unique cloth in lighting varieties from 100 lx to 1300 lx. In addition, 3D recognition and handling accuracy have been confirmed to be practically effective by conducting the recognition/handling experiments under different light conditions.

AB - Human can recognize and handle (pick and place) easily the objects with a variety of different shapes, colors, sizes, and humans’ eyes are adaptable to various light environments with a certain tolerance. However, it is difficult for robots to recognize deformable objects such as cloth, string, etc., especially if an object is unique. Additionally, there have been difficulties for robots with vision sensors (cameras) to accurately detect and handle objects under various light environments. This paper proposes a cloth handling system that recognizes an unique cloth appeared in front of a robot by a photo-model-based approach. The photo-model-based approach has been adopted since the photo-model can be made at once by taking a photo of the unique cloth. In proposed cloths’ pose estimation method, a photo-model projected from 3D to 2D is used, where this system does not need defining the object’s size, shape, design, color and weight. It detects the cloth through model-based matching method and Genetic Algorithm (GA). The handling performance by the proposed method with dual-eyes cameras has been verified, revealing that the proposed system has leeway to recognize and handle the unique cloth in lighting varieties from 100 lx to 1300 lx. In addition, 3D recognition and handling accuracy have been confirmed to be practically effective by conducting the recognition/handling experiments under different light conditions.

KW - Dual-eyes cameras

KW - Genetic Algorithm

KW - Handling

KW - Illumination

KW - Photo-model-based cloth recognition

KW - Visual servoing

UR - http://www.scopus.com/inward/record.url?scp=85063894886&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063894886&partnerID=8YFLogxK

U2 - 10.1299/jamdsm.2018jamdsm0047

DO - 10.1299/jamdsm.2018jamdsm0047

M3 - Article

AN - SCOPUS:85063894886

VL - 12

JO - Journal of Advanced Mechanical Design, Systems and Manufacturing

JF - Journal of Advanced Mechanical Design, Systems and Manufacturing

SN - 1881-3054

IS - 2

ER -