Accuracy improvement of functional attribute recognition by dense CRF considering object shape

Masaki Iizuka, Shuichi Akizuki, Manabu Hashimoto

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a method to recognize functional attributes of everyday objects for vision system of partner robots. On the related research, there is a method to optimize recognition result with dense (fully connected) CRF which use the estimation result of functional attribute for each pixels. However, since this method is optimized from RGB data, it isn't able to sufficiently consider the shape of object, which have a relationship with the function attribute. In the proposed method, the recognition accuracy of functional attributes is improved by considering the object shape with the dense CRF describing the three - dimensional positional relationship. As a result of the experiment, the recognition rate of the proposed method is 77.0 %, which is 3.8 % higher than the related method. In addition, we confirmed that the processing speed is high as a side effect by reducing processing cost by oversegmentation of input data and using high speed identification by Random Forests. The mean processing speed per an object was 109ms in the proposed method.

Original languageEnglish
Pages (from-to)1088-1093
Number of pages6
JournalIEEJ Transactions on Electronics, Information and Systems
Volume138
Issue number9
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Processing
Pixels
Robots
Costs
Experiments

Keywords

  • Affordance
  • Dense CRF
  • Functional attribute
  • Partner robot

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Accuracy improvement of functional attribute recognition by dense CRF considering object shape. / Iizuka, Masaki; Akizuki, Shuichi; Hashimoto, Manabu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 138, No. 9, 01.01.2018, p. 1088-1093.

Research output: Contribution to journalArticle

Iizuka, Masaki ; Akizuki, Shuichi ; Hashimoto, Manabu. / Accuracy improvement of functional attribute recognition by dense CRF considering object shape. In: IEEJ Transactions on Electronics, Information and Systems. 2018 ; Vol. 138, No. 9. pp. 1088-1093.
@article{a53643a11d9e44aa977456cd7a8398ad,
title = "Accuracy improvement of functional attribute recognition by dense CRF considering object shape",
abstract = "In this paper, we propose a method to recognize functional attributes of everyday objects for vision system of partner robots. On the related research, there is a method to optimize recognition result with dense (fully connected) CRF which use the estimation result of functional attribute for each pixels. However, since this method is optimized from RGB data, it isn't able to sufficiently consider the shape of object, which have a relationship with the function attribute. In the proposed method, the recognition accuracy of functional attributes is improved by considering the object shape with the dense CRF describing the three - dimensional positional relationship. As a result of the experiment, the recognition rate of the proposed method is 77.0 {\%}, which is 3.8 {\%} higher than the related method. In addition, we confirmed that the processing speed is high as a side effect by reducing processing cost by oversegmentation of input data and using high speed identification by Random Forests. The mean processing speed per an object was 109ms in the proposed method.",
keywords = "Affordance, Dense CRF, Functional attribute, Partner robot",
author = "Masaki Iizuka and Shuichi Akizuki and Manabu Hashimoto",
year = "2018",
month = "1",
day = "1",
doi = "10.1541/ieejeiss.138.1088",
language = "English",
volume = "138",
pages = "1088--1093",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "9",

}

TY - JOUR

T1 - Accuracy improvement of functional attribute recognition by dense CRF considering object shape

AU - Iizuka, Masaki

AU - Akizuki, Shuichi

AU - Hashimoto, Manabu

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this paper, we propose a method to recognize functional attributes of everyday objects for vision system of partner robots. On the related research, there is a method to optimize recognition result with dense (fully connected) CRF which use the estimation result of functional attribute for each pixels. However, since this method is optimized from RGB data, it isn't able to sufficiently consider the shape of object, which have a relationship with the function attribute. In the proposed method, the recognition accuracy of functional attributes is improved by considering the object shape with the dense CRF describing the three - dimensional positional relationship. As a result of the experiment, the recognition rate of the proposed method is 77.0 %, which is 3.8 % higher than the related method. In addition, we confirmed that the processing speed is high as a side effect by reducing processing cost by oversegmentation of input data and using high speed identification by Random Forests. The mean processing speed per an object was 109ms in the proposed method.

AB - In this paper, we propose a method to recognize functional attributes of everyday objects for vision system of partner robots. On the related research, there is a method to optimize recognition result with dense (fully connected) CRF which use the estimation result of functional attribute for each pixels. However, since this method is optimized from RGB data, it isn't able to sufficiently consider the shape of object, which have a relationship with the function attribute. In the proposed method, the recognition accuracy of functional attributes is improved by considering the object shape with the dense CRF describing the three - dimensional positional relationship. As a result of the experiment, the recognition rate of the proposed method is 77.0 %, which is 3.8 % higher than the related method. In addition, we confirmed that the processing speed is high as a side effect by reducing processing cost by oversegmentation of input data and using high speed identification by Random Forests. The mean processing speed per an object was 109ms in the proposed method.

KW - Affordance

KW - Dense CRF

KW - Functional attribute

KW - Partner robot

UR - http://www.scopus.com/inward/record.url?scp=85052636170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052636170&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.138.1088

DO - 10.1541/ieejeiss.138.1088

M3 - Article

VL - 138

SP - 1088

EP - 1093

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 9

ER -