지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 국제구조공학회 Smart Structures and Systems, An International Journal Smart Structures and Systems, An International Journal Vol.29 No.1
- 발행연도
- 2022.1
- 수록면
- 207 - 220 (14page)
이용수
초록· 키워드
오류제보하기
Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.
목차
등록된 정보가 없습니다.
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Performance Comparison of Mask R-CNN and Deep Crack Algorithms for Crack segmentation
한국콘크리트학회 학술대회 논문집
2023 .05
-
Mask R-CNN을 이용한 물체인식 및 개체분할의 학습 데이터셋 자동 생성
로봇학회 논문지
2019 .03
-
Mask2Former 를 이용한 크랙 시맨틱 분할
제어로봇시스템학회 논문지
2023 .12
-
A deep learning-based vision enhancement method for UAV assisted visual inspection of concrete cracks
Smart Structures and Systems, An International Journal
2021 .01
-
An active learning method with difficulty learning mechanism for crack detection
Smart Structures and Systems, An International Journal
2022 .01
-
Comparison of the Effect of Interpolation on the Mask R-CNN Model
Journal of information and communication convergence engineering
2023 .03
-
Instance Segmentation for phenotyping leaf vegetables using Mask R-CNN
제어로봇시스템학회 국내학술대회 논문집
2023 .06
-
Segmentation applying TAG type label data and Transformer
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
이미지 라벨링 시스템(Label Now)
대한전자공학회 학술대회
2022 .11
-
Estimation of shrimp’s size based on 3D instance segmentation using deep learning technology
제어로봇시스템학회 국내학술대회 논문집
2022 .06
-
Temporal Difference-based Weighted Instance Segmentation Applied on Consecutive Images for Food Recognition
제어로봇시스템학회 논문지
2023 .12
-
이미지 라벨링을 이용한 결함 분류
한국기계가공학회 춘추계학술대회 논문집
2020 .06
-
적외선 카메라 영상에서의 마스크 R-CNN기반 발열객체검출
디지털콘텐츠학회논문지
2018 .06
-
Mask R-CNN과 Semantic Soft Segmentation을 이용한 객체 분할
한국통신학회 학술대회논문집
2020 .02
-
교량 안전점검을 위한 딥러닝 기반 균열 분석에 관한 연구
Proceedings of KIIT Conference
2021 .06
-
압축센싱이 Mask R-CNN 기반의 객체검출에 미치는 영향 분석
한국정보통신학회 종합학술대회 논문집
2022 .05
-
DeepCleanNet: Training Deep Convolutional Neural Network with Extremely Noisy Labels
멀티미디어학회논문지
2020 .11
-
심층학습의 인스턴스 분할을 이용한 시설작물 레이블링
한국지능시스템학회 논문지
2021 .08
-
Mask R-CNN을 이용한 항공 영상에서의 도로 균열 검출
한국산업정보학회논문지
2019 .06
-
SAMT: Shape-aware Multi-task Deep Convolutional Model for Crack Identification
대한전자공학회 학술대회
2023 .06
이 논문의 저자 정보
최근 본 자료
댓글(0)
0