한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

오픈소스 하드웨어와 딥러닝 기반 객체 탐지 알고리즘을 활용한 교내 유동인구 분석

Analysis of Floating Population in Schools Using Open Source Hardware and Deep Learning-Based Object Detection Algorithm

  • 김보람 (부경대학교 공간정보시스템공학과) ;
  • 임윤교 (부경대학교 공간정보시스템공학과) ;
  • 신실 (부경대학교 공간정보시스템공학과) ;
  • 이진혁 (부경대학교 공간정보시스템공학과) ;
  • 추성원 (부경대학교 공간정보시스템공학과) ;
  • 김나경 (부경대학교 공간정보시스템공학과) ;
  • 박미소 (부경대학교 공간정보시스템공학과) ;
  • 윤홍주 (부경대학교 공간정보시스템공학과)
  • 투고 : 2021.11.29
  • 심사 : 2022.02.17
  • 발행 : 2022.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 오픈소스 하드웨어인 라즈베리파이와 딥러닝 기술 기반 객체 탐지 알고리즘을 이용해 부경대학교 교내 유동인구 조사 및 분석을 수행하였다. 라즈베리파이를 이용하여 이미지를 수집한 후 YOLO3의 IMAGEAI, YOLOv5 모델을 사용하여 수집한 이미지의 인물 검출을 진행하였으며 정확도 비교 분석을 위해 Haar-like features, HOG 모델을 사용하였다. 분석결과, 개교기념일로 인한 휴교에 가장 적은 유동인구가 관측되었다. 대체적으로 입구의 유동인구가 출구의 유동인구보다 많았으며, 입구와 출구 모두 학교의 기념일과 행사에 따라 유동인구가 많은 영향을 받는 것으로 나타났다.

In this study, Pukyong National University's floating population survey and analysis were conducted using Raspberry Pie, an open source hardware, and object detection algorithms based on deep learning technology. After collecting images using Raspberry Pie, the person detection of the collected images using YOLO3's IMAGEAI and YOLOv5 models was performed, and Haar-like features and HOG models were used for accuracy comparison analysis. As a result of the analysis, the smallest floating population was observed due to the school anniversary. In general, the floating population at the entrance was larger than the floating population at the exit, and both the entrance and exit were found to be greatly affected by the school's anniversary and events.

키워드

참고문헌

  1. Y. Jeong and T. Moon, "Analysis of Seoul Urban Spatial Structure Using Pedestrian Flow Data - Comparative Study with '2030 Seoul Plan'," J. of The Korean Regional Development Association, vol 26, no. 3, Sept. 2014, pp. 139-158.
  2. H. Kim, "Inference population using night floating population," KOREAN SOCIETY OF CIVIL ENGINEERS, Oct. 2015, pp. 29-30.
  3. J. Bae, M. Kim, S. Yoo, J. Heo, and H. Sohn, "IShelter location-allocation for Tsunami Using Floating Population and Genetic Algorithm," J. of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography., vol. 37, no. 3, June 2019, pp. 157-165. https://doi.org/10.7848/KSGPC.2019.37.3.157
  4. M. Byun and U. Seo, "How to Measure Daytime Population in Urban Streets?: Case of Seoul Pedestrian Flow Survey," The Korean Association for Survey Research, J. Survey Research, vol. 42, no. 2, 2011, pp. 27-50.
  5. H. Lee, J. Lee, M. Kim, H. Nam, H. Mun, and Y. Lee "Measurement the Floating Population of the University Using Raspberry pi," Conf. The Korean Institute of Information Scientists and Engineers, Jeju, Korea, Dec. 2017, pp. 2092-2094.
  6. S. Yang, "Implementation of Fire Detection System Using Raspberry Pi-based SSD," Master's Thesis, Graduate School of Korea Maritime University, 2020.
  7. D. Jeong, T. Jung, and T. Im "Deep learning-based ship object detection and recognition using Raspberry Pi," Conf. Korea Institute Of Communication Sciences, Pyeongchang, Korea, Feb. 2020, pp. 1059-1060.
  8. S. Kim, M. Lee, and H. Yoe, "Design of the Pest Recognition System using Raspberry Pi," J. Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol. 8, no. 11, Nov. 2018, pp. 941-953.
  9. Z. Lin and C. Kim, "Development of Smart Mirror System based on the Raspberry Pi," J. of the KIECS, vol 16, no. 2, Apr. 2021, pp. 379-384.
  10. D. Lee, S. Lee, R. Hwan, and I. Hyuk, "Door Surveillance system using the Raspberry Pi," Proc. of Symp of the Korean Institute of communications and Information Sciences, seoul, korea, Nov. 2015, pp. 424-425.
  11. H. Kim, H. You, and J. Chang, "Development of Realtime Pet Monitoring System by using Raspberry Pi," The Korean Institute of Information Scientists and Engineers, Pyeongchang, korea, Dec. 2016, pp. 1543-1545.
  12. P. Viola and M. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features," Proc. of IEEE Computer Society Conf. On Computer Vision and Pattern Recognition, vol. 1, 2001, pp. 511-518.
  13. J. Kim and E. Kim, "Face Recognition and Temperature Measurement Access Control System using Machine Learning," J. of the KIECS, vol 16, no. 1, Feb. 2021, pp. 197-202.