Interactive Object Recognition through Hypothesis Generation and Confirmation

Md. Altab HOSSAIN; Rahmadi KURNIA; Akio NAKAMURA; Yoshinori KUNO

doi:10.1093/ietisy/e89-d.7.2197

Interactive Object Recognition through Hypothesis Generation and Confirmation

Md. Altab HOSSAIN, Rahmadi KURNIA, Akio NAKAMURA, Yoshinori KUNO

Full Text Views

0

Share
Cite this

Summary :

An effective human-robot interaction is essential for wide penetration of service robots into the market. Such robot needs a vision system to recognize objects. It is, however, difficult to realize vision systems that can work in various conditions. More robust techniques of object recognition and image segmentation are essential. Thus, we have proposed to use the human user's assistance for objects recognition through speech. This paper presents a system that recognizes objects in occlusion and/or multicolor cases using geometric and photometric analysis of images. Based on the analysis results, the system makes a hypothesis of the scene. Then, it asks the user for confirmation by describing the hypothesis. If the hypothesis is not correct, the system generates another hypothesis until it correctly understands the scene. Through experiments on a real mobile robot, we have confirmed the usefulness of the system.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.7 pp.2197-2206

Publication Date: 2006/07/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.7.2197

Type of Manuscript: Special Section PAPER (Special Section on Machine Vision Applications)

Category: Interactive Systems

Cite this

Copy

Md. Altab HOSSAIN, Rahmadi KURNIA, Akio NAKAMURA, Yoshinori KUNO, "Interactive Object Recognition through Hypothesis Generation and Confirmation" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 7, pp. 2197-2206, July 2006, doi: 10.1093/ietisy/e89-d.7.2197.
Abstract: An effective human-robot interaction is essential for wide penetration of service robots into the market. Such robot needs a vision system to recognize objects. It is, however, difficult to realize vision systems that can work in various conditions. More robust techniques of object recognition and image segmentation are essential. Thus, we have proposed to use the human user's assistance for objects recognition through speech. This paper presents a system that recognizes objects in occlusion and/or multicolor cases using geometric and photometric analysis of images. Based on the analysis results, the system makes a hypothesis of the scene. Then, it asks the user for confirmation by describing the hypothesis. If the hypothesis is not correct, the system generates another hypothesis until it correctly understands the scene. Through experiments on a real mobile robot, we have confirmed the usefulness of the system.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.7.2197/_p

Copy

@ARTICLE{e89-d_7_2197,
author={Md. Altab HOSSAIN, Rahmadi KURNIA, Akio NAKAMURA, Yoshinori KUNO, },
journal={IEICE TRANSACTIONS on Information},
title={Interactive Object Recognition through Hypothesis Generation and Confirmation},
year={2006},
volume={E89-D},
number={7},
pages={2197-2206},
abstract={An effective human-robot interaction is essential for wide penetration of service robots into the market. Such robot needs a vision system to recognize objects. It is, however, difficult to realize vision systems that can work in various conditions. More robust techniques of object recognition and image segmentation are essential. Thus, we have proposed to use the human user's assistance for objects recognition through speech. This paper presents a system that recognizes objects in occlusion and/or multicolor cases using geometric and photometric analysis of images. Based on the analysis results, the system makes a hypothesis of the scene. Then, it asks the user for confirmation by describing the hypothesis. If the hypothesis is not correct, the system generates another hypothesis until it correctly understands the scene. Through experiments on a real mobile robot, we have confirmed the usefulness of the system.},
keywords={},
doi={10.1093/ietisy/e89-d.7.2197},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Interactive Object Recognition through Hypothesis Generation and Confirmation
T2 - IEICE TRANSACTIONS on Information
SP - 2197
EP - 2206
AU - Md. Altab HOSSAIN
AU - Rahmadi KURNIA
AU - Akio NAKAMURA
AU - Yoshinori KUNO
PY - 2006
DO - 10.1093/ietisy/e89-d.7.2197
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2006
AB - An effective human-robot interaction is essential for wide penetration of service robots into the market. Such robot needs a vision system to recognize objects. It is, however, difficult to realize vision systems that can work in various conditions. More robust techniques of object recognition and image segmentation are essential. Thus, we have proposed to use the human user's assistance for objects recognition through speech. This paper presents a system that recognizes objects in occlusion and/or multicolor cases using geometric and photometric analysis of images. Based on the analysis results, the system makes a hypothesis of the scene. Then, it asks the user for confirmation by describing the hypothesis. If the hypothesis is not correct, the system generates another hypothesis until it correctly understands the scene. Through experiments on a real mobile robot, we have confirmed the usefulness of the system.
ER -