Object detection based on saliency map using reference image containing complex background

Yasuto Tamura; Atsuo Takanishi; Hiroyuki Masuta; Hun Ok Lim

doi:10.1109/WAC.2014.6936136

Object detection based on saliency map using reference image containing complex background

Yasuto Tamura^*, Atsuo Takanishi, Hiroyuki Masuta, Hun Ok Lim

^*Corresponding author for this work

School of Creative Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

We propose an object detection method based on a saliency map using a reference image containing complex background for service robots. In previous detection methods, images that the user prepares in advance contain mostly simple background. However, in order to make robots perform daily tasks, the robots should be able to detect an object using snapshots that contain a complex background. In order to decrease the effect of features in the background, our proposed method classifies local features based on saliency from images. This paper shows the efficacy of the proposed method; furthermore, we demonstrate that our service robot detects certain objects according to the proposed method.

Original language	English
Title of host publication	World Automation Congress Proceedings
Publisher	IEEE Computer Society
Pages	759-762
Number of pages	4
ISBN (Electronic)	9781889335490
DOIs	https://doi.org/10.1109/WAC.2014.6936136
Publication status	Published - 2014 Oct 24
Event	2014 World Automation Congress, WAC 2014 - Waikoloa, United States Duration: 2014 Aug 3 → 2014 Aug 7

Publication series

Name	World Automation Congress Proceedings
ISSN (Print)	2154-4824
ISSN (Electronic)	2154-4832

Conference

Conference	2014 World Automation Congress, WAC 2014
Country/Territory	United States
City	Waikoloa
Period	14/8/3 → 14/8/7

Keywords

Object Detection
Robot Vision
Saliency Map

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1109/WAC.2014.6936136

Cite this

Tamura, Y, Takanishi, A, Masuta, H & Lim, HO 2014, Object detection based on saliency map using reference image containing complex background. in World Automation Congress Proceedings., 6936136, World Automation Congress Proceedings, IEEE Computer Society, pp. 759-762, 2014 World Automation Congress, WAC 2014, Waikoloa, United States, 14/8/3. https://doi.org/10.1109/WAC.2014.6936136

@inproceedings{944babe45b1b46d5beb9efcb33113d9a,

title = "Object detection based on saliency map using reference image containing complex background",

abstract = "We propose an object detection method based on a saliency map using a reference image containing complex background for service robots. In previous detection methods, images that the user prepares in advance contain mostly simple background. However, in order to make robots perform daily tasks, the robots should be able to detect an object using snapshots that contain a complex background. In order to decrease the effect of features in the background, our proposed method classifies local features based on saliency from images. This paper shows the efficacy of the proposed method; furthermore, we demonstrate that our service robot detects certain objects according to the proposed method.",

keywords = "Object Detection, Robot Vision, Saliency Map",

author = "Yasuto Tamura and Atsuo Takanishi and Hiroyuki Masuta and Lim, {Hun Ok}",

note = "Publisher Copyright: {\textcopyright} 2014 TSI Press.; 2014 World Automation Congress, WAC 2014 ; Conference date: 03-08-2014 Through 07-08-2014",

year = "2014",

month = oct,

day = "24",

doi = "10.1109/WAC.2014.6936136",

language = "English",

series = "World Automation Congress Proceedings",

publisher = "IEEE Computer Society",

pages = "759--762",

booktitle = "World Automation Congress Proceedings",

}

TY - GEN

T1 - Object detection based on saliency map using reference image containing complex background

AU - Tamura, Yasuto

AU - Takanishi, Atsuo

AU - Masuta, Hiroyuki

AU - Lim, Hun Ok

PY - 2014/10/24

Y1 - 2014/10/24

N2 - We propose an object detection method based on a saliency map using a reference image containing complex background for service robots. In previous detection methods, images that the user prepares in advance contain mostly simple background. However, in order to make robots perform daily tasks, the robots should be able to detect an object using snapshots that contain a complex background. In order to decrease the effect of features in the background, our proposed method classifies local features based on saliency from images. This paper shows the efficacy of the proposed method; furthermore, we demonstrate that our service robot detects certain objects according to the proposed method.

AB - We propose an object detection method based on a saliency map using a reference image containing complex background for service robots. In previous detection methods, images that the user prepares in advance contain mostly simple background. However, in order to make robots perform daily tasks, the robots should be able to detect an object using snapshots that contain a complex background. In order to decrease the effect of features in the background, our proposed method classifies local features based on saliency from images. This paper shows the efficacy of the proposed method; furthermore, we demonstrate that our service robot detects certain objects according to the proposed method.

KW - Object Detection

KW - Robot Vision

KW - Saliency Map

UR - http://www.scopus.com/inward/record.url?scp=84908887631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908887631&partnerID=8YFLogxK

U2 - 10.1109/WAC.2014.6936136

DO - 10.1109/WAC.2014.6936136

M3 - Conference contribution

AN - SCOPUS:84908887631

T3 - World Automation Congress Proceedings

SP - 759

EP - 762

BT - World Automation Congress Proceedings

PB - IEEE Computer Society

T2 - 2014 World Automation Congress, WAC 2014

Y2 - 3 August 2014 through 7 August 2014

ER -

Object detection based on saliency map using reference image containing complex background

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this