Semantic knowledge-based bayesian refinement for object recognition

Kun Woo Kim; Gi Hyun Lim; Hyo Won Suh; Il Hong Suh

doi:10.13140/2.1.4683.2329

Semantic knowledge-based bayesian refinement for object recognition

Kun Woo Kim, Gi Hyun Lim, Hyo Won Suh, Il Hong Suh

Machine Learning and Robotics

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

Even if some of previous approaches prove their effectiveness for tightly controlled environments such as industrial settings, dependable object recognition remains difficult in real environments. Thus, this paper proposes a method of robust object recognition effective in real environments. The basic idea is to recognize and predict objects via a combined use of ontology and Bayesian network. To demonstrate the benefits of the proposed approach, a case study is conducted in an actual working environment.

Original language	English
Title of host publication	The 5th International Conference on the Advanced Mechatronics (ICAM2010)
Place of Publication	Japan
Publisher	Japan Society of Mechanical Engineers
Pages	585-590
Number of pages	6
DOIs	https://doi.org/10.13140/2.1.4683.2329
Publication status	Published - Oct 2010
Event	International Conference on Advanced Mechatronics - Osaka University, Toyonaka, Japan Duration: 4 Oct 2010 → 6 Oct 2010

Conference

Conference	International Conference on Advanced Mechatronics
Abbreviated title	ICAM 2010
Country/Territory	Japan
City	Toyonaka
Period	4/10/10 → 6/10/10

Access to Document

10.13140/2.1.4683.2329

Cite this

@inproceedings{3854b1493aca433dad2e5ed94409a29e,

title = "Semantic knowledge-based bayesian refinement for object recognition",

abstract = "Even if some of previous approaches prove their effectiveness for tightly controlled environments such as industrial settings, dependable object recognition remains difficult in real environments. Thus, this paper proposes a method of robust object recognition effective in real environments. The basic idea is to recognize and predict objects via a combined use of ontology and Bayesian network. To demonstrate the benefits of the proposed approach, a case study is conducted in an actual working environment.",

author = "Kim, {Kun Woo} and Lim, {Gi Hyun} and Suh, {Hyo Won} and Suh, {Il Hong}",

year = "2010",

month = oct,

doi = "10.13140/2.1.4683.2329",

language = "English",

pages = "585--590",

booktitle = "The 5th International Conference on the Advanced Mechatronics (ICAM2010)",

publisher = "Japan Society of Mechanical Engineers",

address = "Japan",

note = "International Conference on Advanced Mechatronics, ICAM 2010 ; Conference date: 04-10-2010 Through 06-10-2010",

}

TY - GEN

T1 - Semantic knowledge-based bayesian refinement for object recognition

AU - Kim, Kun Woo

AU - Lim, Gi Hyun

AU - Suh, Hyo Won

AU - Suh, Il Hong

PY - 2010/10

Y1 - 2010/10

N2 - Even if some of previous approaches prove their effectiveness for tightly controlled environments such as industrial settings, dependable object recognition remains difficult in real environments. Thus, this paper proposes a method of robust object recognition effective in real environments. The basic idea is to recognize and predict objects via a combined use of ontology and Bayesian network. To demonstrate the benefits of the proposed approach, a case study is conducted in an actual working environment.

AB - Even if some of previous approaches prove their effectiveness for tightly controlled environments such as industrial settings, dependable object recognition remains difficult in real environments. Thus, this paper proposes a method of robust object recognition effective in real environments. The basic idea is to recognize and predict objects via a combined use of ontology and Bayesian network. To demonstrate the benefits of the proposed approach, a case study is conducted in an actual working environment.

U2 - 10.13140/2.1.4683.2329

DO - 10.13140/2.1.4683.2329

M3 - Conference contribution

SP - 585

EP - 590

BT - The 5th International Conference on the Advanced Mechatronics (ICAM2010)

PB - Japan Society of Mechanical Engineers

CY - Japan

T2 - International Conference on Advanced Mechatronics

Y2 - 4 October 2010 through 6 October 2010

ER -

Semantic knowledge-based bayesian refinement for object recognition

Abstract

Conference

Access to Document

Fingerprint

Cite this