Faster R-CNN을 활용한 GPR 영상에서의 지하배관 위치추적 성능분석
Performance Analysis of Detecting buried pipelines in GPR images using Faster R-CNN
0
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
도심지에는 상ㆍ하수관로, 가스관, 수소관 등 필요에 따라 여러 가지 배관이 매설된다. 매설된 배관은 시간이 경과됨에 따라 균열 등으로 노후화되면서 폭발, 누수 등의 사고 발생 위험을 가지게 된다. 이러한 위험을 방지하기 위해 많은 노후 배관 수리, 교체되지만, 배관의 위치 또한 변경될 수 있다. 변경된 배관의 위치를 확인하지 못하면 배관을 건드려서 사고가 발생할 수 있다. 본 논문에서는 GPR을 사용하여 지하 단면 영상을 얻고, Faster R-CNN을 활용하여 지하 배관의 위치를 추정해보고, augmentation을 적용하여 부족한 데이터를 늘려서 실험을 진행하였다.
Abstract
Various pipes are buried in the city as needed, such as water pipes, gas pipes and hydrogen pipes. As the time passes, buried pipes becomes aged due to crack, etc. these pipes has the risk of accidents such as explosion and leakage. To prevent the risks, many pipes are repaired or replaced, but the location of the pipes can also be changed. Failure to identify the location of the altered pipe may cause an accident by touching the pipe. In this paper, we propose a method to detect buried pipes by gathering the GPR images by using GPR and Learning with Faster R-CNN. Then experiments was carried out by raw data sets and data sets augmentation applied to increase the amount of images.
참고문헌 (11)
- D. Daniels, "Ground penetrating rader" (2004), The Institution of Engineering and Technology Publishing
- 이대영, "CCTV 및 GPR을 이용한 하수관로 결함 및 지반함몰 위험성 평가", 한국지반신소재학회 논문집, 17(3), pp.47~55 (2018), 한국지반신소재학회[DOI]
- M. G. Huici, "Accurate ground penetrating radar numerical modeling for automatic detection and recognition of antipersonnel landmines", Doctoral, pp.2013
- Qingxu Dou, "Real-Time Hyperbola Recognition and Fitting in GPR Data", IEEE Transactions on Geoscience and Remote Sensing, 55(1), pp.51~62 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 이명천, "지뢰 탐지를 위한 지면추종 및 탐지위치 표식에 관한 연구", 한국군사과학기술학회지, 14(6), pp.1002~1008 (2011), 한국군사과학기술학회
- R. Girshick, "Rich feature hierarchies for accurate object detection and semantic segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.580~587 (2014)
- R. Girshick, "Fast R-CNN", 2015International Conference on Computer Vision, pp.1440~1448 (2015)
- Shaoqing Ren, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), pp.1137~1149 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- S. J. Shin, "Analsys of the effect of convolutional neural network model on training and prediction in Faster R-CNN", Journal of Korean Institute of Industrial Engineers, pp.1~5 (2017)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", Proceedings of International Conference on Learning Representations, pp.1~14 (2015)
- C. J. Kim, "Object detection based on data augmentation using image rotation", Journal of Institute of Electronics and Information Engineers, pp.545~548 (2018)