A robust gesture recognition based on depth data

Lee Jaemin, Hironori Takimoto, Hitoshi Yamauchi, Akihiro Kanazawa, Yasue Mitsukura

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

14 Citations (Scopus)

Abstract

In this paper, we propose a novel method for gesture recognition using depth data captured by Microsoft Kinect sensor. Conventionally, the features which have been used for gesture recognition are divided into two parts, hand shape and arm movement. In conventional methods, only two-dimensional hand features are used because human's hand consists of the multiple joint structure. Furthermore, conventional arm movement feature are influenced by environmental changing, such as individual differences in body size, camera position and so on. Therefore, to assist in the recognition, a method of feature extraction is proposed, which involves the hand shape with 3D feature and the arm movement with angle between joints of body. In order to show effectiveness of the proposed method, performance for gesture recognition is compared with conventional methods using Japanese language.

Original languageEnglish
Title of host publicationFCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision
Pages127-131
Number of pages5
DOIs
Publication statusPublished - 2013
Event19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2013 - Incheon, Korea, Republic of
Duration: 2013 Jan 302013 Feb 1

Other

Other19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2013
CountryKorea, Republic of
CityIncheon
Period13/1/3013/2/1

Fingerprint

Gesture recognition
Feature extraction
Cameras
Sensors

Keywords

  • depth sensor
  • hand geesture recognition
  • HMM
  • Image processing

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Jaemin, L., Takimoto, H., Yamauchi, H., Kanazawa, A., & Mitsukura, Y. (2013). A robust gesture recognition based on depth data. In FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision (pp. 127-131). [6485474] https://doi.org/10.1109/FCV.2013.6485474

A robust gesture recognition based on depth data. / Jaemin, Lee; Takimoto, Hironori; Yamauchi, Hitoshi; Kanazawa, Akihiro; Mitsukura, Yasue.

FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013. p. 127-131 6485474.

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

Jaemin, L, Takimoto, H, Yamauchi, H, Kanazawa, A & Mitsukura, Y 2013, A robust gesture recognition based on depth data. in FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision., 6485474, pp. 127-131, 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2013, Incheon, Korea, Republic of, 13/1/30. https://doi.org/10.1109/FCV.2013.6485474
Jaemin L, Takimoto H, Yamauchi H, Kanazawa A, Mitsukura Y. A robust gesture recognition based on depth data. In FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013. p. 127-131. 6485474 https://doi.org/10.1109/FCV.2013.6485474
Jaemin, Lee ; Takimoto, Hironori ; Yamauchi, Hitoshi ; Kanazawa, Akihiro ; Mitsukura, Yasue. / A robust gesture recognition based on depth data. FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013. pp. 127-131
@inproceedings{ea604a2d24dd4539b813127d8d2cd757,
title = "A robust gesture recognition based on depth data",
abstract = "In this paper, we propose a novel method for gesture recognition using depth data captured by Microsoft Kinect sensor. Conventionally, the features which have been used for gesture recognition are divided into two parts, hand shape and arm movement. In conventional methods, only two-dimensional hand features are used because human's hand consists of the multiple joint structure. Furthermore, conventional arm movement feature are influenced by environmental changing, such as individual differences in body size, camera position and so on. Therefore, to assist in the recognition, a method of feature extraction is proposed, which involves the hand shape with 3D feature and the arm movement with angle between joints of body. In order to show effectiveness of the proposed method, performance for gesture recognition is compared with conventional methods using Japanese language.",
keywords = "depth sensor, hand geesture recognition, HMM, Image processing",
author = "Lee Jaemin and Hironori Takimoto and Hitoshi Yamauchi and Akihiro Kanazawa and Yasue Mitsukura",
year = "2013",
doi = "10.1109/FCV.2013.6485474",
language = "English",
isbn = "9781467356206",
pages = "127--131",
booktitle = "FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision",

}

TY - GEN

T1 - A robust gesture recognition based on depth data

AU - Jaemin, Lee

AU - Takimoto, Hironori

AU - Yamauchi, Hitoshi

AU - Kanazawa, Akihiro

AU - Mitsukura, Yasue

PY - 2013

Y1 - 2013

N2 - In this paper, we propose a novel method for gesture recognition using depth data captured by Microsoft Kinect sensor. Conventionally, the features which have been used for gesture recognition are divided into two parts, hand shape and arm movement. In conventional methods, only two-dimensional hand features are used because human's hand consists of the multiple joint structure. Furthermore, conventional arm movement feature are influenced by environmental changing, such as individual differences in body size, camera position and so on. Therefore, to assist in the recognition, a method of feature extraction is proposed, which involves the hand shape with 3D feature and the arm movement with angle between joints of body. In order to show effectiveness of the proposed method, performance for gesture recognition is compared with conventional methods using Japanese language.

AB - In this paper, we propose a novel method for gesture recognition using depth data captured by Microsoft Kinect sensor. Conventionally, the features which have been used for gesture recognition are divided into two parts, hand shape and arm movement. In conventional methods, only two-dimensional hand features are used because human's hand consists of the multiple joint structure. Furthermore, conventional arm movement feature are influenced by environmental changing, such as individual differences in body size, camera position and so on. Therefore, to assist in the recognition, a method of feature extraction is proposed, which involves the hand shape with 3D feature and the arm movement with angle between joints of body. In order to show effectiveness of the proposed method, performance for gesture recognition is compared with conventional methods using Japanese language.

KW - depth sensor

KW - hand geesture recognition

KW - HMM

KW - Image processing

UR - http://www.scopus.com/inward/record.url?scp=84875992858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875992858&partnerID=8YFLogxK

U2 - 10.1109/FCV.2013.6485474

DO - 10.1109/FCV.2013.6485474

M3 - Conference contribution

AN - SCOPUS:84875992858

SN - 9781467356206

SP - 127

EP - 131

BT - FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision

ER -