Real-time upper-body detection and orientation estimation via depth cues for assistive technology

Guang Yang, Mamoru Iwabuchi, Kenryu Nakamura

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

1 Citation (Scopus)

Abstract

Automatic and efficient human pose estimation has great practical value in video surveillance. In this paper, we explore how a consumer depth sensor can assist with upper-body detection and pose estimation more precisely in the field of assistive technology for people with disabilities, and a novel real-time upper-body pose (orientation) estimation method is presented. At first, the Haar cascade based upper-body detection is conducted, and the depth information in a fixed subregion is extracted as the input feature vector. Then, support vector machine (SVM) and naive Bayes classifier are compared for estimating the upper-body orientation. Further, in order to acquire the continuous estimation data during a long time for behavioral analysis, we also adopt the support vector regression (SVR) to train a regression model. The experimental results show the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages13-18
Number of pages6
DOIs
Publication statusPublished - 2013 Nov 4
Externally publishedYes
Event2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore
Duration: 2013 Apr 162013 Apr 19

Publication series

NameProceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

Conference

Conference2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
CountrySingapore
CitySingapore
Period13/4/1613/4/19

Fingerprint

Support vector machines
Classifiers
Sensors

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Yang, G., Iwabuchi, M., & Nakamura, K. (2013). Real-time upper-body detection and orientation estimation via depth cues for assistive technology. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 13-18). [6613817] (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). https://doi.org/10.1109/CIRAT.2013.6613817

Real-time upper-body detection and orientation estimation via depth cues for assistive technology. / Yang, Guang; Iwabuchi, Mamoru; Nakamura, Kenryu.

Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 13-18 6613817 (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013).

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

Yang, G, Iwabuchi, M & Nakamura, K 2013, Real-time upper-body detection and orientation estimation via depth cues for assistive technology. in Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6613817, Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, pp. 13-18, 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, Singapore, 13/4/16. https://doi.org/10.1109/CIRAT.2013.6613817
Yang G, Iwabuchi M, Nakamura K. Real-time upper-body detection and orientation estimation via depth cues for assistive technology. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 13-18. 6613817. (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). https://doi.org/10.1109/CIRAT.2013.6613817
Yang, Guang ; Iwabuchi, Mamoru ; Nakamura, Kenryu. / Real-time upper-body detection and orientation estimation via depth cues for assistive technology. Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 13-18 (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013).
@inproceedings{fcd03e92e368412384571196109775c8,
title = "Real-time upper-body detection and orientation estimation via depth cues for assistive technology",
abstract = "Automatic and efficient human pose estimation has great practical value in video surveillance. In this paper, we explore how a consumer depth sensor can assist with upper-body detection and pose estimation more precisely in the field of assistive technology for people with disabilities, and a novel real-time upper-body pose (orientation) estimation method is presented. At first, the Haar cascade based upper-body detection is conducted, and the depth information in a fixed subregion is extracted as the input feature vector. Then, support vector machine (SVM) and naive Bayes classifier are compared for estimating the upper-body orientation. Further, in order to acquire the continuous estimation data during a long time for behavioral analysis, we also adopt the support vector regression (SVR) to train a regression model. The experimental results show the effectiveness of the proposed method.",
author = "Guang Yang and Mamoru Iwabuchi and Kenryu Nakamura",
year = "2013",
month = "11",
day = "4",
doi = "10.1109/CIRAT.2013.6613817",
language = "English",
isbn = "9781467359078",
series = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",
pages = "13--18",
booktitle = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

}

TY - GEN

T1 - Real-time upper-body detection and orientation estimation via depth cues for assistive technology

AU - Yang, Guang

AU - Iwabuchi, Mamoru

AU - Nakamura, Kenryu

PY - 2013/11/4

Y1 - 2013/11/4

N2 - Automatic and efficient human pose estimation has great practical value in video surveillance. In this paper, we explore how a consumer depth sensor can assist with upper-body detection and pose estimation more precisely in the field of assistive technology for people with disabilities, and a novel real-time upper-body pose (orientation) estimation method is presented. At first, the Haar cascade based upper-body detection is conducted, and the depth information in a fixed subregion is extracted as the input feature vector. Then, support vector machine (SVM) and naive Bayes classifier are compared for estimating the upper-body orientation. Further, in order to acquire the continuous estimation data during a long time for behavioral analysis, we also adopt the support vector regression (SVR) to train a regression model. The experimental results show the effectiveness of the proposed method.

AB - Automatic and efficient human pose estimation has great practical value in video surveillance. In this paper, we explore how a consumer depth sensor can assist with upper-body detection and pose estimation more precisely in the field of assistive technology for people with disabilities, and a novel real-time upper-body pose (orientation) estimation method is presented. At first, the Haar cascade based upper-body detection is conducted, and the depth information in a fixed subregion is extracted as the input feature vector. Then, support vector machine (SVM) and naive Bayes classifier are compared for estimating the upper-body orientation. Further, in order to acquire the continuous estimation data during a long time for behavioral analysis, we also adopt the support vector regression (SVR) to train a regression model. The experimental results show the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84886657042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886657042&partnerID=8YFLogxK

U2 - 10.1109/CIRAT.2013.6613817

DO - 10.1109/CIRAT.2013.6613817

M3 - Conference contribution

AN - SCOPUS:84886657042

SN - 9781467359078

T3 - Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

SP - 13

EP - 18

BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Rehabilitation and Assistive Technologies, CIRAT 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

ER -