The Journal of Korean Institute of Electromagnetic Engineering and Science (한국전자파학회논문지)

The Korean Institute of Electromagnetic Engineering and Science (한국전자파학회)
권호 표지
DOI QR코드

DOI QR Code

Learning-Based People Counting System Using an IR-UWB Radar Sensor

IR-UWB 레이다 센서를 이용한 학습 기반 인원 계수 추정 시스템

  • Choi, Jae-Ho (Department of Electrical and Electronic Engineering, Pohang University of Science and Technology) ;
  • Kim, Ji-Eun (Department of Electrical and Electronic Engineering, Pohang University of Science and Technology) ;
  • Kim, Kyung-Tae (Department of Electrical and Electronic Engineering, Pohang University of Science and Technology)
  • 최재호 (포항공과대학교 전자전기공학과) ;
  • 김지은 (포항공과대학교 전자전기공학과) ;
  • 김경태 (포항공과대학교 전자전기공학과)
  • Received : 2018.11.14
  • Accepted : 2018.12.24
  • Published : 2019.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a real-time system for counting people. The proposed system uses an impulse radio ultra-wideband(IR-UWB) radar to estimate the number of people in a given location. The proposed system uses learning-based classification methods to count people more accurately. In other words, a feature vector database is constructed by exploiting the pattern of reflected signals, which depends on the number of people. Subsequently, a classifier is trained using this database. When a newly received signal data is acquired, the system automatically counts people using the pre-trained classifier. We validated the effectiveness of the proposed algorithm by presenting the results of real-time estimation of the number of people changing from 0 to 10 in an indoor environment.

본 논문에서는 임펄스 무선-초광대역(impulse-radio ultra wideband: IR-UWB) 레이다를 이용하여, 특정 공간 내 존재하는 인원들의 계수를 실시간으로 추정하는 시스템을 제안한다. 제안된 시스템은 정확한 인원 계수 추정을 수행하기 위해 학습 기반의 분류 기법을 사용한다. 즉, 인원수에 의해 달라지는 반사 신호의 패턴에 따라 특징 벡터 데이터베이스(feature vector database)를 형성하고, 형성된 데이터베이스를 이용하여 분류기(classifier)를 학습시킨다. 학습된 분류기를 통해 새로운 신호 수신 시 자동으로 인원 계수 추정을 수행할 수 있다. 실내 환경에서 0명부터 10명까지 변하는 사람들을 실시간으로 추정함으로써, 본 논문에서 제안된 시스템의 효용성을 검증하였다.

Keywords

JJPHCH_2019_v30n1_28_f0001.png 이미지

그림 1. 전 처리 수행 전의 IR-UWB 레이다 신호 Fig. 1. IR-UWB radar signal before applying signal prepro-cessing.

JJPHCH_2019_v30n1_28_f0002.png 이미지

그림 2. 전 처리 수행 후의 IR-UWB 레이다 신호 Fig. 2. IR-UWB radar signal after applying signal prepro-cessing.

JJPHCH_2019_v30n1_28_f0003.png 이미지

그림 3. 변형된 CLEAN 알고리즘 순서도 Fig. 3. The flowchart of modified CLEAN algorithm.

JJPHCH_2019_v30n1_28_f0004.png 이미지

그림 4. 변형된 CLEAN 알고리즘의 임계값 설정 Fig. 4. Threshold settings of modified CLEAN algorithm.

JJPHCH_2019_v30n1_28_f0005.png 이미지

그림 5. 다층 퍼셉트론 분류기 Fig. 5. The multi-layer perceptron classifier.

JJPHCH_2019_v30n1_28_f0006.png 이미지

그림 6. 실험 장소 1(트인 실내 공간) Fig. 6. Place of experiment 1(open indoor space).

JJPHCH_2019_v30n1_28_f0007.png 이미지

그림 7. 실험 장소 2(막힌 실내 공간) Fig. 7. Place of experiment 2(closed indoor space).

JJPHCH_2019_v30n1_28_f0008.png 이미지

그림 8. 실시간 인원 추정 Fig. 8. Real-time people counting.

JJPHCH_2019_v30n1_28_f0009.png 이미지

그림 9. 트인 실내 공간에서의 계수 추정 오차 행렬 Fig. 9. Confusion matrix of people counting in open indoor space.

JJPHCH_2019_v30n1_28_f0010.png 이미지

그림 10. 닫힌 실내 공간에서의 계수 추정 오차 행렬 Fig. 10. Confusion matrix of people counting in closed in-door space.

JJPHCH_2019_v30n1_28_f0011.png 이미지

그림 11. 트인 환경과 닫힌 환경에서의 계수 추정 결과 Fig. 11. The result of people counting in open and closed environment.

표 1. IR-UWB 레이다 사양 Table 1. The specification of an IR-UWB radar.

JJPHCH_2019_v30n1_28_t0001.png 이미지

References

  1. A. Zanella, N. Bui, A. Castellani, L. Vangelista, and M. Zorzi, "Internet of things for smart cities," IEEE Internet of Things Journal, vol. 1, no. 1, pp. 22-32, Feb. 2014. https://doi.org/10.1109/JIOT.2014.2306328
  2. W. Balid, H. H. Refai, "On the development of self-powered IoT sensor for real-time traffic monitoring in smart cities," 2017 IEEE Sensors, Glasgow, Oct. 2017, pp. 1-3.
  3. T. Joseph, R. Jenu, A. K. Assis, V. A. S. Kumar, P. M. Sasi, and G. Alexander, "IoT middleware for smart city: An integrated and centrally managed IoT middleware for smart city," in 2017 IEEE Region 10 Symposium(TENSYMP), Cochin, Jul. 2017, pp. 1-5.
  4. C. Zeng, H. Ma, "Robust head-shoulder detection by PCAbased multilevel HOG-LBP detector for people counting," in 2010 20th International Conference on Pattern Recognition, Istanbul, Aug. 2010, pp. 2069-2072.
  5. Y. L. Hou, G. K. H. Pang, "People counting and human detection in a challenging situation," IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, vol. 41, no. 1, pp. 24-33, Jan. 2011. https://doi.org/10.1109/TSMCA.2010.2064299
  6. C. N. Padole, H. Proenca, "Periocular recognition: Analysis of performance degradation factors," in 2012 5th IAPR International Conference on Biometrics(ICB), New Delhi, Mar. 2012, pp. 439-445.
  7. J. W. Choi, X. Quan, and S. H. Cho, "Bi-directional passing people counting system based on IR-UWB radar sensors," IEEE Internet of Things Journal, vol. 5, no. 2, pp. 512-522, Apr. 2018. https://doi.org/10.1109/JIOT.2017.2714181
  8. F. Wahl, M. Milenkovic, and O. Amft, "A distributed pir-based approach for estimating people count in office environments," in 2012 IEEE 15th International Conference on Computational Science and Engineering, Nicosia, Dec. 2012, pp. 640-647.
  9. J. D. Taylor, Introduction to Ultra-Wideband Radar Systems, Boca Raton, CRC Press, 1994.
  10. J. W. Choi, S. S. Nam, and S. H. Cho, "Multi-human detection algorithm based on an impulse radio ultrawideband radar system," IEEE Access, vol. 4, pp. 10300-10309, Jan. 2017. https://doi.org/10.1109/ACCESS.2016.2647226
  11. J. W. Choi, J. H. Kim, and S. H. Cho, "A counting algorithm for multiple objects using an IR-UWB radar system," in 2012 3rd IEEE International Conference on Network Infrastructure and Digital Content, Beijing, Sep. 2012, pp. 591-595.
  12. J. W. Choi, S. H. Cho, "A crowdedness measurement algorithm using an IR-UWB radar sensor," in International Conference on Future Communication, Information and Computer Science(FCICS), Beijing, May 2014, pp. 119-122.
  13. X. Yang, W. Yin, and L. Zhang, "People counting based on CNN using IR-UWB radar," in 2017 IEEE/CIC International Conference on Communications in China (ICCC), Qingdao, Oct. 2017, pp. 1-5.
  14. J. W. Choi, D. H. Yim, and S. H. Cho, "People counting based on an IR-UWB radar sensor," IEEE Sensors Journal, vol. 17, no. 17, pp. 5717-5727, Sep. 2017. https://doi.org/10.1109/JSEN.2017.2723766
  15. K. T. Kim, D. K. Seo, and H. T. Kim "Efficient radar target recognition using the MUSIC algorithm and invariant features," IEEE Transactions on Antennas and Propagation, vol. 50, no. 3, pp. 325-337, Mar. 2002. https://doi.org/10.1109/8.999623
  16. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, New York, NY, John Wiley & Sons, 2012.
  17. C. M. Van der Walt, E. Barnard, "Data characteristics that determine classifier performance," SAIEE Africa Research Journal, vol. 98, no. 3, pp. 87-93, Nov. 2006.