A Study on Automatically Information Collection of Underground Facility Using R-CNN Techniques

doi:10.15683/kosdi.2023.9.30.689

All Issue

2023 Vol.19, Issue 3 Preview Page Next Page

Original Article

A Study on Automatically Information Collection of Underground Facility Using R-CNN Techniques R-CNN 기법을 이용한 지중매설물 제원 정보 자동 추출 연구: 박현석¹*ㆍ홍기만²ㆍ조용성³
Hyunsuk Park¹*, Kiman Hong², Yongsung Cho³; ¹Senior Researcher, Department of Highway&Transportation Research, Korea Institute of Civil Engineering and Building Technology, Goyang, Republic of Korea
²Associate Research Fellow, Department of Urban Spatial Environment, Yongin Research Institute, Yongin, Republic of Korea
³Researcher Specialist, Department of Highway&Transportation Research, Korea Institute of Civil Engineering and Building Technology, Goyang, Republic of Korea

30 September 2023. pp. 689-697

PDF

Abstract

Purpose: The purpose of this study is to automatically extract information on underground facilities using a general-purpose smartphone in the process of applying the mini-trenching method. Method: Data sets for image learning were collected under various conditions such as day and night, height, and angle, and the object detection algorithm used the R-CNN algorithm. Result: As a result of the study, F1-Score was applied as a performance evaluation index that can consider the average of accurate predictions and reproduction rates at the same time, and F1-Score was 0.76. Conclusion: The results of this study showed that it was possible to extract information on underground buried materials based on smartphones, but it is necessary to improve the precision and accuracy of the algorithm through additional securing of learning data and on-site demonstration.

Keywords

Urderground Facility

R-CNN

Image Training

Information Extraction

Mini Trenching Method

연구목적: 본 연구는 미니트렌칭 공법 적용 과정에서 범용 스마트폰을 이용하여 지중매설물의 정보를 자동 추출하는데 목적이 있다. 연구방법: 이미지 학습을 위한 데이터 셋은 주야간, 높이, 각도 등의 다양한 조건에서 수집하였으며, 객체 검지알고리즘은 R-CNN 알고리즘을 이용하였다. 연구결과: 성능평가 지표는 정확한 예측과 재현율의 평균을 동시에 고려할 수 있는 F1-Score를 적용하였으며, 학습결과 F1-Score는 0.76으로 나타났다. 결론: 본 연구의 결과는 스마트폰 기반의 지중매설물 정보 추출이 가능한 것으로 나타났으나, 학습데이터의 추가적인 확보와 현장 실증 등을 통해 알고리즘의 정밀성 및 정확성을 향상시킬 필요가 있을 것으로 판단된다.

키워드

지중매설물

R-CNN

이미지 학습

정보 추출

미니트렌칭

References

Girshick R, Donahue J, Darrell T, Malik J. (2014). "Rich feature hierarchies for accurate object detection and semantic segmentation." 2014 IEEE Conference on Computer Vision and Pattern Recognition, Ohio, US, pp. 580-587. 10.1109/CVPR.2014.81
Ivan, M., Abhijeet, A., Virat, J. (2020). "Real-time space occupancy sensing and human motion analysis using deep learning for indoor air quality control." Automation in Construction, US, pp. 1-15.
Jung, Y.S. (2022). A Study on the UHF RFID Signal Attenuation for Underground Facility Management, Masters Dissertation, Chung-Ang University.
Kim, D., Jeong, J., Park, S., Go, J., Yeom, C. (2020). "A study on the application of optimal evacuation route through evacuation simulation system in case of fire." Journal of the Society of Disaster Information, Vol. 16, No. 1, pp. 96-110.
Kim, J.Y. (2020). A Study on Object Detection Algorithm using Retinanet based on BiFPN, Masters Dissertation, Sunchon National University.
Kim, M.C. (2022). Development of Rebar Counting Model Using Image Obtained from Drone by Introducing Faster R-CNN, Masters Dissertation, Hanyang University.
Kim, T.D. (2017). "A study on the development of Intelligent Markup Indicator (IMI) technology for underground facilities management using IoT." The Journal of The Institute of Internet, Broadcasting and Communication, Vol. 17, No. 3, pp. 129-136. 10.7236/JIIBC.2017.17.3.129
Korea Institute of Civil Engineering and Building Technology (2020). Development of Technologies and Management Method of Trenching about Aerial Utility Cables for Urban Regeneration, KICT 2020-042, Goyang.
Lee, Y.W., Kim, S.H. (2012). "A study on the development of Smart Information Mark and the method for Underground facility management." Journal of the Korean Cadastre Information Association, Vol. 14, No. 2, pp. 77-89.
Maria Navin J.R, Pankaja, R. (2016). "Performance analysis of text classification algorithms using confusion matrix." International Journal of Engineering and Technical Research, Vol. 6, No. 4, pp. 75-77.
Park, K.H., Kim, I.S., An, D.H. (2019). "An integrated IoT underground utility management system using pole-type utility indicators." Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, Vol. 9, No. 1, pp. 41-50.
Press release (2021). https://www.korea.kr/briefing/pressReleaseView.do?newsId=156434944
Son, G., Son, S. (2021). "A study on fire alarm test of Iot multi-fire detector combined smoke/CO and smoke/ temperature sensors." Journal of the Society of Disaster Information, Vol. 17, No. 2, pp. 236-244.

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 : 19
No :3
Pages :689-697
DOI :https://doi.org/10.15683/kosdi.2023.9.30.689

[1] Girshick R, Donahue J, Darrell T, Malik J. (2014). "Rich feature hierarchies for accurate object detection and semantic segmentation." 2014 IEEE Conference on Computer Vision and Pattern Recognition, Ohio, US, pp. 580-587. 10.1109/CVPR.2014.81

[2] Ivan, M., Abhijeet, A., Virat, J. (2020). "Real-time space occupancy sensing and human motion analysis using deep learning for indoor air quality control." Automation in Construction, US, pp. 1-15.

[3] Jung, Y.S. (2022). A Study on the UHF RFID Signal Attenuation for Underground Facility Management, Masters Dissertation, Chung-Ang University.

[4] Kim, D., Jeong, J., Park, S., Go, J., Yeom, C. (2020). "A study on the application of optimal evacuation route through evacuation simulation system in case of fire." Journal of the Society of Disaster Information, Vol. 16, No. 1, pp. 96-110.

[5] Kim, J.Y. (2020). A Study on Object Detection Algorithm using Retinanet based on BiFPN, Masters Dissertation, Sunchon National University.

[6] Kim, M.C. (2022). Development of Rebar Counting Model Using Image Obtained from Drone by Introducing Faster R-CNN, Masters Dissertation, Hanyang University.

[7] Kim, T.D. (2017). "A study on the development of Intelligent Markup Indicator (IMI) technology for underground facilities management using IoT." The Journal of The Institute of Internet, Broadcasting and Communication, Vol. 17, No. 3, pp. 129-136. 10.7236/JIIBC.2017.17.3.129

[8] Korea Institute of Civil Engineering and Building Technology (2020). Development of Technologies and Management Method of Trenching about Aerial Utility Cables for Urban Regeneration, KICT 2020-042, Goyang.

[9] Lee, Y.W., Kim, S.H. (2012). "A study on the development of Smart Information Mark and the method for Underground facility management." Journal of the Korean Cadastre Information Association, Vol. 14, No. 2, pp. 77-89.

[10] Maria Navin J.R, Pankaja, R. (2016). "Performance analysis of text classification algorithms using confusion matrix." International Journal of Engineering and Technical Research, Vol. 6, No. 4, pp. 75-77.

[11] Park, K.H., Kim, I.S., An, D.H. (2019). "An integrated IoT underground utility management system using pole-type utility indicators." Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, Vol. 9, No. 1, pp. 41-50.

[12] Press release (2021). https://www.korea.kr/briefing/pressReleaseView.do?newsId=156434944

[13] Son, G., Son, S. (2021). "A study on fire alarm test of Iot multi-fire detector combined smoke/CO and smoke/ temperature sensors." Journal of the Society of Disaster Information, Vol. 17, No. 2, pp. 236-244.

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

All Issue