The Journal of Korea Institute of Information, Electronics, and Communication Technology (한국정보전자통신기술학회논문지)

Korea Information Electronic Communication Technology (한국정보전자통신기술학회)
권호 표지
DOI QR코드

DOI QR Code

Fall Detection System Using Motion Vector

움직임 벡터를 이용한 낙상 감지 시스템

  • Kim, Sang-Soo (Division of Information Communication, Kunsan National University) ;
  • Kim, Sun-Woo (Division of Information Communication, Kunsan National University) ;
  • Choi, Yeon-Sung (Division of Information Communication, Kunsan National University)
  • Received : 2016.01.29
  • Accepted : 2016.01.10
  • Published : 2016.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, Author of this article presents a system to ensure the safety of residents in case the residents occurs an fall situation. Author of this article use weighted difference image and motion vector. Proposed system suggested the fall detection algorithm using weighted difference image and motion vector. Fall detection algorithm showed a success rate of 85% ~ 97.1% through 150 experiments. Proposed algorithm showed a litter higher or similar success rate than the existing camera based system.

본 논문에서는 움직임 벡터를 이용한 낙상 감지 시스템에 관해 기술한다. 두드러진 움직임을 위한 가중치 차영상 기법, 움직임 벡터를 이용하여 인간이라고 판단되는 블랍을 검출하고, 추출된 움직임 벡터를 이용하여 낙상 여부를 판단한다. 기존의 영상 기반 낙상 감지 시스템의 경우 특정 방향으로 낙상이 발생하는 경우에만 낙상 감지에 성공하였지만 제안 시스템의 경우 다양한 각도에서 낙상이 발생하여도 상황 판단이 가능하다는 장점이 있다. 실험을 위해서 150개의 상황을 연출하였으며, 약 85% ~ 97.1% 낙상 상황 판단 성공률을 보였다.

Keywords

References

  1. S.W Kim, "A Circadian Life Pattern Modeling and Anomaly Detection Method for Elders Living Alone", Journal of KISS:Computing practices, Vol.7, No7, pp. 399-408, 2011
  2. G.Viron, "Behavioral Patterns of Older Adults in Assisted Living", IEEE Transactions, Vol. 12, No.3, pp.387-398, 2008
  3. http://www.ginje.go.kr/
  4. http://1661-2129.or.kr/
  5. T. H Kim, "Salient Motion Information Detection Technique using Weighted Subtraction Image and Motion Vector", Master's thesis, Kunsan National University, 2006
  6. S.W.Kim, Y.S.Choi, H.K.Yang, "Analysis of Human Activity Using motion Vector", KIMICS, Vol.15, no.2, pp.157-16, 2011.
  7. J. H. Park, "Block Error Concealment using Motion Vector Direction Embedding", Master's thesis, Kyungpook National University, 2004

Cited by

  1. Development of Personalized Urination Recognition Technology Using Smart Bands vol.21, pp.Suppl 1, 2017, https://doi.org/10.5213/inj.1734886.443
  2. Design and Implementation of a Fall Recognition System Based on 3-Axis Acceleration Data and Altitude Data for Improvement of Fall Recognition Accuracy and Convenience vol.18, pp.1, 2016, https://doi.org/10.14801/jkiit.2020.18.1.115