Development of a Deep Learning-based Fire Extinguisher Object Detection Model in Underground Utility Tunnels

doi:10.15683/kosdi.2022.12.31.922

All Issue

2022 Vol.18, Issue 4 Preview Page Next Page

Original Article

Development of a Deep Learning-based Fire Extinguisher Object Detection Model in Underground Utility Tunnels 딥러닝 기반 지하 공동구 내 소화기 객체 탐지 모델 개발: 박상미¹ㆍ홍창희²*ㆍ박승화³ㆍ이재욱⁴ㆍ김정수⁵
Sangmi Park¹, Changhee Hong²*, Seunghwa Park³, Jaewook Lee⁴, Jeongsoo Kim⁵; ¹Post-Doctor Researcher, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction and BIM Cluster, Goyang, Republic of Korea
²Research Fellow, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction and BIM Cluster, Goyang, Republic of Korea
³Senior Researcher, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction and BIM Cluster, Goyang, Republic of Korea
⁴Senior Researcher, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction and BIM Cluster, Goyang, Republic of Korea
⁵Research Specialist, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction and BIM Cluster, Goyang, Republic of Korea

31 December 2022. pp. 922-929

PDF

Abstract

Purpose: The purpose of this paper is to develop a deep learning model to detect fire extinguishers in images taken from CCTVs in underground utility tunnels. Method: Various fire extinguisher images were collected for detection of fire extinguishers in the running-based underground utility tunnel, and a model applying the One-stage Detector method was developed based on the CNN algorithm. Result: The detection rate of fire extinguishers photographed within 10m through CCTV video in the underground common area is over 96%, showing excellent detection rate. However, it was confirmed that the fire extinguisher object detection rate drops sharply at a distance of 10m or more, in a state where it is difficult to see with the naked eye. Conclusion: This paper develops a model for detecting fire extinguisher objects in underground common areas, and the model shows high performance, and it is judged that it can be used for underground common area digital twin model synchronizing.

Keywords

Underground Utility Tunnel

Deep Learning

Object Detection

Fire Extinguisher

Digital Twin

연구목적: 본 논문은 지하공동구 내 CCTV에서 촬영된 영상에서 소화기를 탐지하기 위해 딥러닝 모델을 개발하는데 목적이 있다. 연구방법: 딥러닝 기반 지하공동구 내 소화기 탐지를 위해 다양한 소화기 이미지를 수집하였으며 CNN 알고리즘을 기반으로 하여 One-stage Detector 방식을 적용한 모델을 개발하였다. 연구결과: 지하공동구 내 CCTV 영상을 통해 10m 이내의 거리에서 촬영되는 소화기의 검출률은 96%이상으로 우수한 검출률을 보여준다. 다만 10m 이상의 거리에서는 육안으로도 확인하기 힘든 상태로, 소화기 객체 검출률이 급격하게 낮아지는 것을 확인하였다. 결론: 본 논문은 지하공동구 내 소화기 객체를 검출하는 모델을 개발하였으며, 해당 모델이 높은 성능을 보여 지하공동구 디지털트윈 모델 연동에 활용할 수 있을 것으로 판단된다.

키워드

지하공동구

딥러닝

객체검출

소화기

디지털트윈

References

Han, S.H., Chae, S., Hassan, S.A., Rahim, T., Shin, S.Y. (2020). "Video-based traffic accident prevention safety system using deep learning." The Journal of Korean Institute of Communications and Information Sciences, Vol. 48, No. 8, pp. 1399-1406. 10.7840/kics.2020.45.8.1399
Hu, J., Gao, X., Wu, H., Gao, S. (2019). "Detection of workers without the helmets in videos based on YOLO V3." 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, Huaqiao, China. 10.1109/CISP-BMEI48845.2019.8966045
Kim, J.H., Lee, T.H., Han, Y., Byun, H.J. (2021). "A study on the design and implementation of multi-disaster drone system using deep learning-based object recognition and optimal path planning." KIPS Transactions on Computer and Communication Systems, Vol. 10, No. 4, pp.117-122.
Kim, J.S., Lee, C.W., Park, S.H., Lee, J.H., Hong, C.H. (2020). "Development of fire detection model for underground utility facilities using deep learning: Training data supplement and bias optimization." Journal of the Korea Academia-Industrial cooperation Society, Vol. 21, No. 12, pp. 320-330.
Kim, S.H., Lee, W.J., Park, Y.S., Lee, Y.H. (2017). "Machine learning based human detection and danger recognition technique." The KIPS Conference, Jeju, Vol. 24, No. 1, pp.1035-1036.
Kumar, S.S., Wang, M.Z., Abraham, D.M. and Mohammad. R.J. (2018). "Deep Learning - based automated detection of sewer defects in CCTV videos." Journal of Computing in Civil Engineering, Vol. 34, No. 1. 10.1061/(ASCE)CP.1943-5487.0000866
Lee, S.Y., Huynh. T.C., Park, J.H., Kim, J.T. (2019). "Bolt-loosening detection using vision-based deep learning algorithm and image processing method." Computational Structural Engineering Institute of Korea, Vol. 32, No. 4, pp. 265-272. 10.7734/COSEIK.2019.32.4.265
Park, S.H., Hong, C.H., Lee, Y.H. (2021). "A study on a digital twin based update methodology of spatial facilities information in underground urban utility tunnels." Proceedings of the KAIS Spring Conference, Jeju, Korea.
Shin, Y.H., Yun, J.S., Seo, S.H., Chung, J.M. (2017). "Deployment of network resources for enhancement of disaster response capabilities with deep learning and augmented reality." Journal of Internet Computing and Services, Vol. 15, No. 5, pp.69-77.
Xiao, B., Kang, S.C. (2021). "Development of an image data set of construction machines for deep learning object detection." Journal of Computing in Civil Engineering, Vol. 35, No. 2. 10.1061/(ASCE)CP.1943-5487.0000945

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 18
No :4
Pages :922-929
DOI :https://doi.org/10.15683/kosdi.2022.12.31.922

[1] Han, S.H., Chae, S., Hassan, S.A., Rahim, T., Shin, S.Y. (2020). "Video-based traffic accident prevention safety system using deep learning." The Journal of Korean Institute of Communications and Information Sciences, Vol. 48, No. 8, pp. 1399-1406. 10.7840/kics.2020.45.8.1399

[2] Hu, J., Gao, X., Wu, H., Gao, S. (2019). "Detection of workers without the helmets in videos based on YOLO V3." 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, Huaqiao, China. 10.1109/CISP-BMEI48845.2019.8966045

[3] Kim, J.H., Lee, T.H., Han, Y., Byun, H.J. (2021). "A study on the design and implementation of multi-disaster drone system using deep learning-based object recognition and optimal path planning." KIPS Transactions on Computer and Communication Systems, Vol. 10, No. 4, pp.117-122.

[4] Kim, J.S., Lee, C.W., Park, S.H., Lee, J.H., Hong, C.H. (2020). "Development of fire detection model for underground utility facilities using deep learning: Training data supplement and bias optimization." Journal of the Korea Academia-Industrial cooperation Society, Vol. 21, No. 12, pp. 320-330.

[5] Kim, S.H., Lee, W.J., Park, Y.S., Lee, Y.H. (2017). "Machine learning based human detection and danger recognition technique." The KIPS Conference, Jeju, Vol. 24, No. 1, pp.1035-1036.

[6] Kumar, S.S., Wang, M.Z., Abraham, D.M. and Mohammad. R.J. (2018). "Deep Learning - based automated detection of sewer defects in CCTV videos." Journal of Computing in Civil Engineering, Vol. 34, No. 1. 10.1061/(ASCE)CP.1943-5487.0000866

[7] Lee, S.Y., Huynh. T.C., Park, J.H., Kim, J.T. (2019). "Bolt-loosening detection using vision-based deep learning algorithm and image processing method." Computational Structural Engineering Institute of Korea, Vol. 32, No. 4, pp. 265-272. 10.7734/COSEIK.2019.32.4.265

[8] Park, S.H., Hong, C.H., Lee, Y.H. (2021). "A study on a digital twin based update methodology of spatial facilities information in underground urban utility tunnels." Proceedings of the KAIS Spring Conference, Jeju, Korea.

[9] Shin, Y.H., Yun, J.S., Seo, S.H., Chung, J.M. (2017). "Deployment of network resources for enhancement of disaster response capabilities with deep learning and augmented reality." Journal of Internet Computing and Services, Vol. 15, No. 5, pp.69-77.

[10] Xiao, B., Kang, S.C. (2021). "Development of an image data set of construction machines for deep learning object detection." Journal of Computing in Civil Engineering, Vol. 35, No. 2. 10.1061/(ASCE)CP.1943-5487.0000945

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue