Eating and drinking recognition via integrated information of head directions and joint positions in a group

Naoto Ienaga, Yuko Ozasa, Hideo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recent years have seen the introduction of service robots as waiters or waitresses in restaurants and cafes. In such venues, it is common for customers to visit in groups as well as for them to engage in conversation while eating and drinking. It is important for cyber serving staff to understand whether they are eating and drinking, or not, in order to wait on tables at appropriate times. In this paper, we present a method by which the robots can recognize eating and drinking actions performed by individuals in a group. Our approach uses the positions of joints in the human body as a feature and long short-term memory to achieve a recognition task on time-series data. We also used head directions in our method, as we assumed that it is effective for recognition in a group. The information garnered from head directions and joint positions is integrated via logistic regression and employed in recognition. The results show that this yielded the highest accuracy and effectiveness of the robots' tasks.

Original languageEnglish
Title of host publicationICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods
PublisherSciTePress
Pages527-533
Number of pages7
Volume2017-January
ISBN (Electronic)9789897582226
Publication statusPublished - 2017 Jan 1
Event6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017 - Porto, Portugal
Duration: 2017 Feb 242017 Feb 26

Other

Other6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017
CountryPortugal
CityPorto
Period17/2/2417/2/26

Fingerprint

Robots
Logistics
Time series
Long short-term memory

Keywords

  • Action recognition
  • Information fusion
  • Long short-term memory

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ienaga, N., Ozasa, Y., & Saito, H. (2017). Eating and drinking recognition via integrated information of head directions and joint positions in a group. In ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (Vol. 2017-January, pp. 527-533). SciTePress.

Eating and drinking recognition via integrated information of head directions and joint positions in a group. / Ienaga, Naoto; Ozasa, Yuko; Saito, Hideo.

ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. Vol. 2017-January SciTePress, 2017. p. 527-533.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ienaga, N, Ozasa, Y & Saito, H 2017, Eating and drinking recognition via integrated information of head directions and joint positions in a group. in ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. vol. 2017-January, SciTePress, pp. 527-533, 6th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2017, Porto, Portugal, 17/2/24.
Ienaga N, Ozasa Y, Saito H. Eating and drinking recognition via integrated information of head directions and joint positions in a group. In ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. Vol. 2017-January. SciTePress. 2017. p. 527-533
Ienaga, Naoto ; Ozasa, Yuko ; Saito, Hideo. / Eating and drinking recognition via integrated information of head directions and joint positions in a group. ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. Vol. 2017-January SciTePress, 2017. pp. 527-533
@inproceedings{00163c08ffb44a96b3352c7b4a5a34cf,
title = "Eating and drinking recognition via integrated information of head directions and joint positions in a group",
abstract = "Recent years have seen the introduction of service robots as waiters or waitresses in restaurants and cafes. In such venues, it is common for customers to visit in groups as well as for them to engage in conversation while eating and drinking. It is important for cyber serving staff to understand whether they are eating and drinking, or not, in order to wait on tables at appropriate times. In this paper, we present a method by which the robots can recognize eating and drinking actions performed by individuals in a group. Our approach uses the positions of joints in the human body as a feature and long short-term memory to achieve a recognition task on time-series data. We also used head directions in our method, as we assumed that it is effective for recognition in a group. The information garnered from head directions and joint positions is integrated via logistic regression and employed in recognition. The results show that this yielded the highest accuracy and effectiveness of the robots' tasks.",
keywords = "Action recognition, Information fusion, Long short-term memory",
author = "Naoto Ienaga and Yuko Ozasa and Hideo Saito",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "2017-January",
pages = "527--533",
booktitle = "ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods",
publisher = "SciTePress",

}

TY - GEN

T1 - Eating and drinking recognition via integrated information of head directions and joint positions in a group

AU - Ienaga, Naoto

AU - Ozasa, Yuko

AU - Saito, Hideo

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Recent years have seen the introduction of service robots as waiters or waitresses in restaurants and cafes. In such venues, it is common for customers to visit in groups as well as for them to engage in conversation while eating and drinking. It is important for cyber serving staff to understand whether they are eating and drinking, or not, in order to wait on tables at appropriate times. In this paper, we present a method by which the robots can recognize eating and drinking actions performed by individuals in a group. Our approach uses the positions of joints in the human body as a feature and long short-term memory to achieve a recognition task on time-series data. We also used head directions in our method, as we assumed that it is effective for recognition in a group. The information garnered from head directions and joint positions is integrated via logistic regression and employed in recognition. The results show that this yielded the highest accuracy and effectiveness of the robots' tasks.

AB - Recent years have seen the introduction of service robots as waiters or waitresses in restaurants and cafes. In such venues, it is common for customers to visit in groups as well as for them to engage in conversation while eating and drinking. It is important for cyber serving staff to understand whether they are eating and drinking, or not, in order to wait on tables at appropriate times. In this paper, we present a method by which the robots can recognize eating and drinking actions performed by individuals in a group. Our approach uses the positions of joints in the human body as a feature and long short-term memory to achieve a recognition task on time-series data. We also used head directions in our method, as we assumed that it is effective for recognition in a group. The information garnered from head directions and joint positions is integrated via logistic regression and employed in recognition. The results show that this yielded the highest accuracy and effectiveness of the robots' tasks.

KW - Action recognition

KW - Information fusion

KW - Long short-term memory

UR - http://www.scopus.com/inward/record.url?scp=85049486434&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049486434&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85049486434

VL - 2017-January

SP - 527

EP - 533

BT - ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods

PB - SciTePress

ER -