DOI QR코드

DOI QR Code

Incoming and Outgoing Human Matching Using Similarity Metrics for Occupancy Sensor

점유센서를 위한 유사성 메트릭을 이용한 입출입 사람 매칭

  • Woo, Youngje (Dept. of Computer and Communications Engineering, Kangwon National University) ;
  • Jeong, Jaejoon (Dept. of Computer and Communications Engineering, Kangwon National University) ;
  • Choi, Changyeol (Dept. of Computer and Communications Engineering, Kangwon National University) ;
  • Kim, Manbae (Dept. of Computer and Communications Engineering, Kangwon National University)
  • 우영제 (강원대학교 컴퓨터정보통신공학과) ;
  • 정재준 (강원대학교 컴퓨터정보통신공학과) ;
  • 최창열 (강원대학교 컴퓨터정보통신공학과) ;
  • 김만배 (강원대학교 컴퓨터정보통신공학과)
  • Received : 2019.01.04
  • Accepted : 2019.03.08
  • Published : 2019.03.30

Abstract

The main functionality of occupancy sensors is to determine the existence of humans in the space. If the space is occupied, a light is on and for vacancy, the light automatically turns off. In this letter, the functionality is realized by the utilization of color information. The color information of incoming people is saved. For outgoing people, their color distribution is compared with the saved information, thus providing the recognition of the outgoing people. For the comparison, four similarity metrics are examined to validate the proposed method.

점유센서의 주요 기능은 공간에 사람이 존재하는지를 결정하는 것이다. 사람이 있으면 점등하고, 반대이면 소등하게 된다. 모션 검출, 객체 추적 등의 방법이 있지만, 본 레터에서는 이 기능의 구현에 컬러를 활용한다. 사람의 컬러정보를 이용하여 입실하는 사람들의 정보를 저장하고, 퇴실하면 저장된 컬러정보와 비교하여 퇴실하는 사람을 인식하는 기법이다. 4가지 유사성 메트릭을 이용하여 성능을 검증하였다.

Keywords

BSGHC3_2019_v24n2_353_f0001.png 이미지

그림 1. 제안 방법의 흐름도 Fig. 1. The flow diagram of the proposed method

BSGHC3_2019_v24n2_353_f0002.png 이미지

그림 2. 연속 영상의 바운딩박스, 전경마스크. 및 배경영상 (a) 한명 입실, (b) 한명 퇴실, 및 (c) 두명 퇴실 Fig. 2. The bounding box and foreground mask of subsequent images. (a) single incoming people, (b) single outgoing people, and (c) two outgoing people

표 1. 입실 및 퇴실의 유사성 메트릭 출력값. A, B, C, D는 사람이고, C+B는 C, B가 동시에 퇴실하는 것임. single outgoing people에서 bold 숫자는 가장 우수한 점수를 가리킴. Two outgoing people에서는 청색값은 가장 우수한 2개를 표시하고, 적색값은 검출오류를 표시함 Table 1. Similarity metric values of incoming and outgoing cases. A~D indicates people and C+B contains outgoing C and B. In single outgoing people, bold number indicates the best value. In two outgoing people, blue numbers indicate the best two values and red numbers indicate the misdetection

BSGHC3_2019_v24n2_353_t0001.png 이미지

References

  1. Liu, S. Nguang, and A. Partridge, "Occupancy inference using pyroelectric infrared sensors through Hidden Markov Model", IEEE Sensors Journal, 16(4), Feb. 2016.
  2. F. Wahl, M. Milenkovic, and O. Amft, "A distributed PIR-based approach for estimating people count in office environments", IEEE Conf. on Computational Sci. and Eng., 2012.
  3. J. Gil and M. Kim, "Real-time people occupancy detection by camera vision sensor", Journal of Broadcast Engineering, Vol. 22, No. 6, Nov. 2017.
  4. Y. Benezeth, H. Laurent, B. Emile, and C. Rosenberger, "Towards a sensor for detecting human presence and characterizing activity", Energy and Buildings, 43, 2011.
  5. D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking", IEEE Trans. Pattern Anal. Mach. Intell., 25(5):564-577, May 2003. https://doi.org/10.1109/TPAMI.2003.1195991
  6. J. Lee and J. Yoo, "Real-time face tracking method using improved Camshift", Journal of Broadcast Engineering, Vol. 21, No. 6, Nov. 2016.
  7. A. Elgammal, R. Duraiswami, and L. Davis, "Probabilistic tracking in joint feature-spatial spaces", IEEE Conf. Comp. Vision Pattern Recognition, pp. 781-788, 2003.
  8. M. Zakai, "General distance criteria," IEEE Trans. Info. Theory, vol.IT-10, no. 1, pp. 94-95, Jan. 1964. https://doi.org/10.1109/TIT.1964.1053633