DOI QR코드

DOI QR Code

The input device system with hand motion using hand tracking technique of CamShift algorithm

CamShift 알고리즘의 Hand Tracking 기법을 응용한 Hand Motion 입력 장치 시스템

  • Jeon, Yu-Na (Hanshin University, School of Computer Engineering) ;
  • Kim, Soo-Ji (Hanshin University, School of Computer Engineering) ;
  • Lee, Chang-Hoon (Hanshin University, School of Computer Engineering) ;
  • Kim, Hyeong-Ryul (Hanshin University, School of Computer Engineering) ;
  • Lee, Sung-Koo (Hanshin University, School of Computer Engineering)
  • Received : 2015.01.26
  • Accepted : 2015.02.28
  • Published : 2015.02.28

Abstract

The existing input device is limited to keyboard and mouse. However, recently new type of input device has been developed in response to requests from users. To reflect this trend we propose the new type of input device that gives instruction as analyzing the hand motion of image without special device. After binarizing the skin color area using Cam-Shift method and tracking, it recognizes the hand motion by inputting the finger areas and the angles from the palm center point, which are separated through labeling, into four cardinal directions and counting them. In cases when specific background was not set and without gloves, the recognition rate remained approximately at 75 percent. However, when specific background was set and the person wore red gloves, the recognition rate increased to 90.2 percent due to reduction in noise.

기존의 대표적인 입력장치는 키보드, 마우스 등으로 한정적이었으나 최근 들어 사용자들의 다양한 요구에 따라 새로운 형태의 입력장치들이 개발되는 추세이다. 이러한 추세에 맞춰 특수한 device 없이 영상의 hand motion을 분석해 명령을 부여하는 새로운 형태의 입력장치를 제안한다. Cam-Shift 기법으로 skin color 영역을 이진화 하여 tracking 한 후, labeling을 통해 분리한 손가락 영역과 손 중심점과의 각도를 동서남북으로 구분해 counting하여 손동작을 인식한다. 손동작에 대한 입력은 맨손에 배경처리를 하지 않은 경우 약 76.8%의 낮은 인식률을 보였으나, 붉은색 장갑을 착용하고 배경을 지정해 줄 경우 잡영 제거의 영향으로 인식률이 90.2%까지 향상된다.

Keywords

References

  1. Bai yu, Sang-Yun Park, Yun-Sik Kim, In-Gab Jeong, Soo-Yol Ok, Eung-Joo Lee, Park Sang-Yun, Kim Yun-Sik, Jeong In-Gab, Ok Soo-Yol, Lee Eung-Joo, "Hand tracking and hand gesture recognition for human computer interaction", Korea Multimedia Society Conference, vol.14, no.2, pp.182-193, 2011
  2. Gwangha Jeon, Jongseok Um,"(A)Study on online real-time strategy game by using hand tracking in augmented reality", Korea Multimedia Society Conference, vol.12, no12, pp.1761-1768, 2009
  3. Ho-Sik Park, Cheol-soo Bae, "Face and Hand Tracking Algorithm for Sign Language Recognition", Communications and Networks, vol.31, no.11, pp.1071-1076, 2006
  4. Shan Caifeng, Tan Tieniu, Wei Yucheng, "Real-time hand tracking using a mean shift embedded particle filter", Pattern Recognition, vol.40, no.7, pp.1958-1970, 2006 https://doi.org/10.1016/j.patcog.2006.12.012
  5. Yonjae Kim, Simon Leonard, Azad Shademan, Axel Krieger, Peter C. W. Kim,"Kinect technology for hand tracking control of surgical robots: technical and surgical skill comparison to current robotic masters", Surgical Endoscopy, vol.28, no.6, pp.1993-2000, 2013 https://doi.org/10.1007/s00464-013-3383-8
  6. Kwang-woon Choi, Da-woon Jeong, Suk-han Lee, Jong-soo Choi, "Interaction Augmented Reality System using a Hand Motion", Korea Multimedia Society Conference, vol.15, no.4, pp.425-438, 2012
  7. Sae-Bom Lee, Il-Hong Jung, "A Design and Implementation of Natural User Interface System Using Kinect", Journal of Digital Contents Society, vol.15, no4, pp.473-480, 2014 https://doi.org/10.9728/dcs.2014.15.4.473

Cited by

  1. Celebrity-indexed video retrieval application using face recognition and tracking vol.19, pp.11, 2015, https://doi.org/10.9728/dcs.2018.19.11.2049