RGB-D camera-based hand shape recognition for human-robot interaction

Junyeong Choi, Byung Kuk Seo, Daeseon Lee, Hanhoon Park, Jong-Il Park

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

5 Citations (Scopus)

Abstract

Hand is the most popularly used tool for human-robot interaction. Therefore, this paper proposes a Kinect-based hand shape recognition method for human-robot interaction. Kinect can capture color and depth images simultaneously and its SDK provides functions to track the human skeleton. Therefore, the proposed method can detect hands robustly by using the skeleton and depth information. In results, it can recognize various hand shapes based on contour analysis with a high recognition rate (95% on average) and works in real-time (over 30 frames/sec).

Original languageEnglish
Title of host publication2013 44th International Symposium on Robotics, ISR 2013
DOIs
StatePublished - 2013 Dec 1
Event2013 44th IEEE International Symposium on Robotics, ISR 2013 - Seoul, Korea, Republic of
Duration: 2013 Oct 242013 Oct 26

Publication series

Name2013 44th International Symposium on Robotics, ISR 2013

Other

Other2013 44th IEEE International Symposium on Robotics, ISR 2013
CountryKorea, Republic of
CitySeoul
Period13/10/2413/10/26

Fingerprint

Human robot interaction
End effectors
Cameras
Color

Keywords

  • Hand shape recognition
  • Kinect
  • human-robot interaction
  • interface

Cite this

Choi, J., Seo, B. K., Lee, D., Park, H., & Park, J-I. (2013). RGB-D camera-based hand shape recognition for human-robot interaction. In 2013 44th International Symposium on Robotics, ISR 2013 [6695627] (2013 44th International Symposium on Robotics, ISR 2013). https://doi.org/10.1109/ISR.2013.6695627
Choi, Junyeong ; Seo, Byung Kuk ; Lee, Daeseon ; Park, Hanhoon ; Park, Jong-Il. / RGB-D camera-based hand shape recognition for human-robot interaction. 2013 44th International Symposium on Robotics, ISR 2013. 2013. (2013 44th International Symposium on Robotics, ISR 2013).
@inproceedings{495c72c396b24878a93b0ebdb395795c,
title = "RGB-D camera-based hand shape recognition for human-robot interaction",
abstract = "Hand is the most popularly used tool for human-robot interaction. Therefore, this paper proposes a Kinect-based hand shape recognition method for human-robot interaction. Kinect can capture color and depth images simultaneously and its SDK provides functions to track the human skeleton. Therefore, the proposed method can detect hands robustly by using the skeleton and depth information. In results, it can recognize various hand shapes based on contour analysis with a high recognition rate (95{\%} on average) and works in real-time (over 30 frames/sec).",
keywords = "Hand shape recognition, Kinect, human-robot interaction, interface",
author = "Junyeong Choi and Seo, {Byung Kuk} and Daeseon Lee and Hanhoon Park and Jong-Il Park",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ISR.2013.6695627",
language = "English",
isbn = "9781479911738",
series = "2013 44th International Symposium on Robotics, ISR 2013",
booktitle = "2013 44th International Symposium on Robotics, ISR 2013",

}

Choi, J, Seo, BK, Lee, D, Park, H & Park, J-I 2013, RGB-D camera-based hand shape recognition for human-robot interaction. in 2013 44th International Symposium on Robotics, ISR 2013., 6695627, 2013 44th International Symposium on Robotics, ISR 2013, 2013 44th IEEE International Symposium on Robotics, ISR 2013, Seoul, Korea, Republic of, 13/10/24. https://doi.org/10.1109/ISR.2013.6695627

RGB-D camera-based hand shape recognition for human-robot interaction. / Choi, Junyeong; Seo, Byung Kuk; Lee, Daeseon; Park, Hanhoon; Park, Jong-Il.

2013 44th International Symposium on Robotics, ISR 2013. 2013. 6695627 (2013 44th International Symposium on Robotics, ISR 2013).

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

TY - GEN

T1 - RGB-D camera-based hand shape recognition for human-robot interaction

AU - Choi, Junyeong

AU - Seo, Byung Kuk

AU - Lee, Daeseon

AU - Park, Hanhoon

AU - Park, Jong-Il

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Hand is the most popularly used tool for human-robot interaction. Therefore, this paper proposes a Kinect-based hand shape recognition method for human-robot interaction. Kinect can capture color and depth images simultaneously and its SDK provides functions to track the human skeleton. Therefore, the proposed method can detect hands robustly by using the skeleton and depth information. In results, it can recognize various hand shapes based on contour analysis with a high recognition rate (95% on average) and works in real-time (over 30 frames/sec).

AB - Hand is the most popularly used tool for human-robot interaction. Therefore, this paper proposes a Kinect-based hand shape recognition method for human-robot interaction. Kinect can capture color and depth images simultaneously and its SDK provides functions to track the human skeleton. Therefore, the proposed method can detect hands robustly by using the skeleton and depth information. In results, it can recognize various hand shapes based on contour analysis with a high recognition rate (95% on average) and works in real-time (over 30 frames/sec).

KW - Hand shape recognition

KW - Kinect

KW - human-robot interaction

KW - interface

UR - http://www.scopus.com/inward/record.url?scp=84893239664&partnerID=8YFLogxK

U2 - 10.1109/ISR.2013.6695627

DO - 10.1109/ISR.2013.6695627

M3 - Conference contribution

AN - SCOPUS:84893239664

SN - 9781479911738

T3 - 2013 44th International Symposium on Robotics, ISR 2013

BT - 2013 44th International Symposium on Robotics, ISR 2013

ER -

Choi J, Seo BK, Lee D, Park H, Park J-I. RGB-D camera-based hand shape recognition for human-robot interaction. In 2013 44th International Symposium on Robotics, ISR 2013. 2013. 6695627. (2013 44th International Symposium on Robotics, ISR 2013). https://doi.org/10.1109/ISR.2013.6695627