[논문]딥러닝 기반 선박 부식 자동 검출을 위한 이미지 전처리 방안 연구

윤광호; 오상진; 신성철

doi:10.21289/ksic.2022.25.4.573

딥러닝 기반 선박 부식 자동 검출을 위한 이미지 전처리 방안 연구
A Study on Image Preprocessing Methods for Automatic Detection of Ship Corrosion Based on Deep Learning 원문보기

한국산업융합학회 논문집 = Journal of the Korean Society of Industry Convergence, v.25 no.4/1, 2022년, pp.573 - 586

윤광호 (부산대학교 조선해양공학과) , 오상진 (부산대학교 조선해양공학과) , 신성철 (부산대학교 조선해양공학과)

Abstract ▼ AI-Helper

Corrosion can cause dangerous and expensive damage and failures of ship hulls and equipment. Therefore, it is necessary to maintain the vessel by periodic corrosion inspections. During visual inspection, many corrosion locations are inaccessible for many reasons, especially safety's point of view. Including subjective decisions of inspectors is one of the issues of visual inspection. Automation of visual inspection is tried by many pieces of research. In this study, we propose image preprocessing methods by image patch segmentation and thresholding. YOLOv5 was used as an object detection model after the image preprocessing. Finally, it was evaluated that corrosion detection performance using the proposed method was improved in terms of mean average precision.

주제어

표/그림 (18)

그림 Fig. 1 Flowchart of the proposed corrosion detection methodology. Image processing is performed before and after the inference step
그림 Fig. 2 Preprocessing through image patch segmentation. Apply overlap between patches to prevent missing corrosion
그림 Fig. 3 Raw image and thresholded image. Emphasize corrosion by limiting HSV range
그림 Fig. 4 Dataset organization. Total dataset, 75% of them were randomly selected and used as training dataset whereas the remaining 25% were used as test dataset
그림 Fig. 5 Dataset of patch image. Patches that do not contain corrosion are excluded from the data composition
그림 Fig. 7 Structure of Bottleneck module
그림 Fig. 6 Architecture of YOLOv5 network
그림 Fig. 8 Structure of BottleneckCSP module
그림 Fig. 9 Structure of SPP module
그림 Fig. 10 Loss function using IoU
그림 Fig. 11 Loss function using GIoU
표 Table 1. GIoU algorithm as Loss
표 Table 2. Confusion matrix
그림 Fig. 12 Loss Graph. The blue line is the train loss according to the epoch, and the red line is the test loss according to the epoch
그림 Fig. 13 PR curve for the training and test dataset. (a) Training PR curve. (b) Test PR curve
그림 Fig. 14 Confusion matrix. (a) Results of the raw image training model on the entire test dataset, (b) Results of the preprocessed image training model on the entire test dataset, (c) Results of the raw image training model on the test data having the red-color background, (d) Results of the preprocessed image training model on the test data having the red-color background
그림 Fig. 15 Detecting corrosion f rom test dataset and corrosion l ocation mask image. (a) circular and l inear corrosion, (b) circular corrosion, (c) linear corrosion, (d) corrosion with a red background.
표 Table 3. Performance indicators for the preprocessed and raw images

참고문헌 (18)

S. Kim, "Apparatus on Corrosion Protection and Marine Corrosion of Ship," Journal of The Korean Institute of Surface Engineering, Vol. 44, No. 3, pp.105-116, (2011).

원문보기 상세보기
Khayatazad, M., De Pue, L., and De Waele, W. "Detection of corrosion on steel structures using automated image processing," Developments in the Built Environment, vol. 3, pp.100022, (2020).

상세보기
Bonnin-Pascual, F., and Ortiz, A. "Chapter Corrosion Detection for Automated Visual Inspection," (2014).
Hoang, N. D. "Image processing-based pitting corrosion detection using metaheuristic optimized multilevel image thresholding and machine-learning approaches," Mathematical Problems in Engineering, (2020).
Chu, M., and Thuerey, N. "Data-driven synthesis of smoke flows with CNN-based feature descriptors," ACM Transactions on Graphics (TOG), Vol. 36, No. 4, pp.1-14, (2017).
D. Kim, S. Boo, H. Hong,W. Yeo, and N. Lee, "Machine Vision-based Defect Detection Using Deep Learning Algorithm," The Korean Society For Nondestructive Testing, Vol. 40, No. 1, pp.47-52, (2020).
Yu, L., Yang, E., Luo, C., and Ren, P. "AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection," Journal of Ambient Intelligence and Humanized Computing, pp. 1-12, (2021).
Chen, Q., Wen, X., Lu, S., Sun, D. "Corrosion detection for large steel structure base on uav integrated with image processing system," In IOP Conference Series: Materials Science and Engineering, Vol. 608, No. 1, pp.012020, (2019).
Cha, Y. J., Choi, W., Suh, G., Mahmoudkhani, S., Buyukozturk, O. "Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types," Computer-Aided Civil and Infrastructure Engineering, Vol. 33, No. 9, pp.731-747, (2018).

상세보기
Zhang, S., Deng, X., Lu, Y., Hong, S., Kong, Z., Peng, Y., and Luo, Y. "A channel attention based deep neural network for automatic metallic corrosion detection," Journal of Building Engineering, Vol. 42, pp.103046, (2021).

상세보기
Katsamenis, I., Protopapadakis, E., Doulamis, A., Doulamis, N., Voulodimos, A. "Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation," In International Symposium on Visual Computing, pp.160-169, (2020).
Yao, Y., Yang, Y., Wang, Y., and Zhao, X. "Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network." Applied Ocean Research, Vol. 90, pp.101823, (2019).

상세보기
Petricca, L., Moss, T., Figueroa, G., and Broen, S. "Corrosion detection using AI: a comparison of standard computer vision techniques and deep learning model," In Proceedings of the Sixth International Conference on Computer Science, Engineering and Information Technology, Vol. 91, pp.91-99, (2016).
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. "You only look once: Unified, real-time object detection," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.779-788, (2016).
Fang, Y., Guo, X., Chen, K., Zhou, Z., and Ye, Q. "Accurate and Automated Detection of Surface Knots on Sawn Timbers Using YOLO-V5 Model," BioResources, Vol. 16, No. 3, (2021).

상세보기
Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. "A real-time apple targets detection method for picking robot based on improved YOLOv5," Remote Sensing, Vol. 13, No. 9, pp.1619, (2021).

상세보기
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S., "Generalized intersection over union: A metric and a loss for bounding box regression," In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.658-666, (2019).
Everingham, M., Eslami, S. A., Van Gool, L., Williams, C. K., Winn, J., and Zisserman, A. "The pascal visual object classes challenge: A retrospective," International journal of computer vision, Vol. 111, No. 1, pp.98-136, (2015).

상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증