A classification method of motion database using hidden Markov model

Ayaka Matsui, Satoshi Nishimura, Seiichiro Katsura

研究成果: Conference contribution

1 引用 (Scopus)

抄録

This paper proposes a classification method of a stored motion-data. Robotic technology has made progress, and robots are demanded to cooperate with human. To realize the human and robot exist together, a motion recognition system is needed. In the conventional method, the stored motion-data is classified in advance to search the motion quickly and accurately. However, the task of the classification will be very complex when the stored data is increased. Therefore, the classification system of stored data automatically is required. Since the human motion is time series information and unsteady signal, a hidden Markov Model is used as the probability models. Additionally, this paper shows that Kullback-Leiblaer divergence indicates the similarity index of the stored motion. At this time, the motion is classified according to the acceleration information, which includes the pure force and position information. The validity of the proposed method is confirmed by simulations.

元の言語English
ホスト出版物のタイトルIEEE International Symposium on Industrial Electronics
出版者Institute of Electrical and Electronics Engineers Inc.
ページ2232-2237
ページ数6
ISBN(印刷物)9781479923991
DOI
出版物ステータスPublished - 2014
イベント2014 IEEE 23rd International Symposium on Industrial Electronics, ISIE 2014 - Istanbul, Turkey
継続期間: 2014 6 12014 6 4

Other

Other2014 IEEE 23rd International Symposium on Industrial Electronics, ISIE 2014
Turkey
Istanbul
期間14/6/114/6/4

Fingerprint

Hidden Markov models
Robots
Time series
Robotics

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering

これを引用

Matsui, A., Nishimura, S., & Katsura, S. (2014). A classification method of motion database using hidden Markov model. : IEEE International Symposium on Industrial Electronics (pp. 2232-2237). [6864965] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIE.2014.6864965

A classification method of motion database using hidden Markov model. / Matsui, Ayaka; Nishimura, Satoshi; Katsura, Seiichiro.

IEEE International Symposium on Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2232-2237 6864965.

研究成果: Conference contribution

Matsui, A, Nishimura, S & Katsura, S 2014, A classification method of motion database using hidden Markov model. : IEEE International Symposium on Industrial Electronics., 6864965, Institute of Electrical and Electronics Engineers Inc., pp. 2232-2237, 2014 IEEE 23rd International Symposium on Industrial Electronics, ISIE 2014, Istanbul, Turkey, 14/6/1. https://doi.org/10.1109/ISIE.2014.6864965
Matsui A, Nishimura S, Katsura S. A classification method of motion database using hidden Markov model. : IEEE International Symposium on Industrial Electronics. Institute of Electrical and Electronics Engineers Inc. 2014. p. 2232-2237. 6864965 https://doi.org/10.1109/ISIE.2014.6864965
Matsui, Ayaka ; Nishimura, Satoshi ; Katsura, Seiichiro. / A classification method of motion database using hidden Markov model. IEEE International Symposium on Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 2232-2237
@inproceedings{4364a8cdab634d7a9d2b694c75df3c85,
title = "A classification method of motion database using hidden Markov model",
abstract = "This paper proposes a classification method of a stored motion-data. Robotic technology has made progress, and robots are demanded to cooperate with human. To realize the human and robot exist together, a motion recognition system is needed. In the conventional method, the stored motion-data is classified in advance to search the motion quickly and accurately. However, the task of the classification will be very complex when the stored data is increased. Therefore, the classification system of stored data automatically is required. Since the human motion is time series information and unsteady signal, a hidden Markov Model is used as the probability models. Additionally, this paper shows that Kullback-Leiblaer divergence indicates the similarity index of the stored motion. At this time, the motion is classified according to the acceleration information, which includes the pure force and position information. The validity of the proposed method is confirmed by simulations.",
author = "Ayaka Matsui and Satoshi Nishimura and Seiichiro Katsura",
year = "2014",
doi = "10.1109/ISIE.2014.6864965",
language = "English",
isbn = "9781479923991",
pages = "2232--2237",
booktitle = "IEEE International Symposium on Industrial Electronics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A classification method of motion database using hidden Markov model

AU - Matsui, Ayaka

AU - Nishimura, Satoshi

AU - Katsura, Seiichiro

PY - 2014

Y1 - 2014

N2 - This paper proposes a classification method of a stored motion-data. Robotic technology has made progress, and robots are demanded to cooperate with human. To realize the human and robot exist together, a motion recognition system is needed. In the conventional method, the stored motion-data is classified in advance to search the motion quickly and accurately. However, the task of the classification will be very complex when the stored data is increased. Therefore, the classification system of stored data automatically is required. Since the human motion is time series information and unsteady signal, a hidden Markov Model is used as the probability models. Additionally, this paper shows that Kullback-Leiblaer divergence indicates the similarity index of the stored motion. At this time, the motion is classified according to the acceleration information, which includes the pure force and position information. The validity of the proposed method is confirmed by simulations.

AB - This paper proposes a classification method of a stored motion-data. Robotic technology has made progress, and robots are demanded to cooperate with human. To realize the human and robot exist together, a motion recognition system is needed. In the conventional method, the stored motion-data is classified in advance to search the motion quickly and accurately. However, the task of the classification will be very complex when the stored data is increased. Therefore, the classification system of stored data automatically is required. Since the human motion is time series information and unsteady signal, a hidden Markov Model is used as the probability models. Additionally, this paper shows that Kullback-Leiblaer divergence indicates the similarity index of the stored motion. At this time, the motion is classified according to the acceleration information, which includes the pure force and position information. The validity of the proposed method is confirmed by simulations.

UR - http://www.scopus.com/inward/record.url?scp=84907342277&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907342277&partnerID=8YFLogxK

U2 - 10.1109/ISIE.2014.6864965

DO - 10.1109/ISIE.2014.6864965

M3 - Conference contribution

AN - SCOPUS:84907342277

SN - 9781479923991

SP - 2232

EP - 2237

BT - IEEE International Symposium on Industrial Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -