전기전자학회논문지 (Journal of IKEEE)

  • 제23권3호
  • /
  • Pages.777-784
  • /
  • 2019
  • /
  • 1226-7244(pISSN)
  • /
  • 2288-243X(eISSN)
한국전기전자학회 (Institute of Korean Electrical and Electronics Engineers)
권호 표지
DOI QR코드

DOI QR Code

유도형 전력선 통신과 연동된 SSD 기반 화재인식 및 알림 시스템

SSD-based Fire Recognition and Notification System Linked with Power Line Communication

  • Yang, Seung-Ho (Dept. of Electronics and Communications Engineering, Korea Maritime & Ocean University) ;
  • Sohn, Kyung-Rak (Dept. of Electronics and Communications Engineering, Korea Maritime & Ocean University) ;
  • Jeong, Jae-Hwan (Dept. of Electronics and Communications Engineering, Korea Maritime & Ocean University) ;
  • Kim, Hyun-Sik (Mattron Corp.)
  • 투고 : 2019.08.29
  • 심사 : 2019.09.14
  • 발행 : 2019.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

인적이 드문 한적한 곳이나 산악 지역에서 화재가 발생 하였을 때 화재 상황을 정확하게 파악하고 적절한 초동 대처를 한다면 피해를 최소화할 수 있으므로 사전 화재인지시스템과 자동알림시스템이 요구된다. 본 연구에서는 객체인식을 위한 딥러닝 알고리즘 중 Faster-RCNN 및 SSD(single shot multibox detecter)을 사용한 화재 인식시스템을 전력선 통신과 연동하여 자동알림시스템을 시연하였으며 향 후 고압송전망을 이용한 산불화재 감시에 응용 가능함을 제시하였다. 학습된 모델을 장착한 라즈베리파이에 파이카메라를 설치하여 화재 영상인식을 수행하였으며, 검출된 화재영상은 유도형 전력선 통신망을 통하여 모니터링 PC로 전송하였다. 학습 모델별 라즈베리파이에서의 초당 프레임 율은 Faster-RCNN의 경우 0.05 fps, SSD의 경우 1.4 fps로 SSD의 처리속도가 Faster-RCNN 보다 28배 정도 빨랐다.

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

키워드

참고문헌

  1. S-H. Lee, B.-J. Shin, B.-D. Song, S.-J. An, J.-D. Kim, H.-J. Lee, "Wild Fire Monitoring System using the Image Matching," J. Korea Contents Society, vol.13, no.6, pp.40-47, 2013. DOI: 10.5392/JKCA.2013.13.06.040
  2. J. H. Son, Y. Huh, Y. G. Byun, K. Y. Yu, Y. I. Kim, "Designing and Building a Fire Monitoring Web GIS System Using MODIS Image-Using ArcIMS 4.0," J. GIS Association of Korea, vol.14, no.1, pp.151-161, 2006.
  3. K. Y. Kim, K. E. Lee, J. H. Han, "Forest fire Detection System using IoT-based drones," Proceeding of Korea Information Science Society, pp.157-159, 2016.
  4. D. Y. Yun, S. H. Kim, "A Design of Fire Monitoring System Based On Unmaned Helicopter and Sensor Network," J. Korean Institute of Intelligent Systems, vol.17, no.2, pp.173-178, 2007. DOI: 10.5391/JKIIS.2007.17.2.173
  5. Y-J. Kim, E.-G. Kim, "Real-Time Fire Detection based on CNN and Grad-CAM," J. Korea Institute of Information and Communication Engineering, vol.22, no.12, pp.1596-1603, 2018. https://doi.org/10.6109/JKIICE.2018.22.12.1596
  6. J-J. Kim, J-K. Ryu, D-K. Kwak, S-J. Byun, "A Study on Flame Detection using Faster R-CNN and Image Augmentation Techniques," J. Korean Electrical and Electronics Engineering, vol.22, no.4, pp.1079-1087, 2018.
  7. S-W. Bang, "Implementation of Image based Fire Detection System Using Convolution Neural Network, " J. Korea Institute of Electronic Communication Sciences. pp.331-336, vol.12, no.2, 2017. DOI: 10.6109/jkiice.2016.20.9.1649
  8. A. M. Tonello and A. Pittolo, "Considerations on narrowband and broadband power line communication for smart grids," IEEE Intl. Conf. Smart Grid Comm., pp.13-18, 2016. DOI: 10.1109/SmartGridComm.2015.7436269
  9. A. Korsonen and J. Aholoa, "Comparison of signal coupling methods for power line communication between a motor and an inverter," IET Electric Power Applications, vol.4, no.6, pp.431-440, 2010. DOI: 10.1049/iet-epa.2009.0114
  10. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.39, pp.1137-1149, 2017. https://doi.org/10.1109/TPAMI.2016.2577031
  11. Liu, Wei, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg. "SSD: Single shot multibox detector," European conference on computer vision, pp.21-37, 2016.
  12. S-J. Kim, M-H. Lee, H. Yoe, "Design of the Pest Recognition System using Raspberry Pi," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol.8, no.11, pp.941-953, 2018. DOI: 10.21742/AJMAHS.2018.11.84
  13. S-H. Yang, J-H. Jung, H-S. Kim, and K-R. Sohn, "Implementation of Soft Magnetic Core Type Coupler for Broadband Power Line Communication," J. KICS, vol.44, no.4, pp.693-700, 2019. DOI: 10.7840/kics.2019.44.4.693