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.31 No.4
- 발행연도
- 2023.4
- 수록면
- 383 - 392 (10page)
이용수
초록· 키워드
오류제보하기
Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.
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 Backbone Networks for Multi-Tasking in Self-Driving Operations
제어로봇시스템학회 국제학술대회 논문집
2022 .11
-
Multi-Task Deep Learning Design and Training Tool for Unified Visual Driving Scene Understanding
제어로봇시스템학회 국제학술대회 논문집
2019 .10
-
Mask2Former 를 이용한 크랙 시맨틱 분할
제어로봇시스템학회 논문지
2023 .12
-
Deep learning-based post-disaster building inspection with channel-wise attention and semi-supervised learning
Smart Structures and Systems, An International Journal
2023 .04
-
SAMT: Shape-aware Multi-task Deep Convolutional Model for Crack Identification
대한전자공학회 학술대회
2023 .06
-
자율주행용 멀티 태스크 러닝 기반 경량 딥러닝 모델 구조에 대한 연구
대한전자공학회 학술대회
2024 .06
-
Ensemble-based deep learning for autonomous bridge component and damage segmentation leveraging Nested Reg-UNet
Smart Structures and Systems, An International Journal
2023 .04
-
A hierarchical semantic segmentation framework for computer vision-based bridge damage detection
Smart Structures and Systems, An International Journal
2023 .04
-
Thin Single Crystal Si Wafers Formed by Spalling
한국에너지학회 학술발표회
2016 .04
-
Spalling 공정을 위한 레이저 측면 가공 기술
한국태양에너지학회 학술대회논문집
2018 .04
-
딥러닝을 이용한 이미지 기반의 콘크리트 균열 및 박락 탐지
대한토목학회지
2018 .08
-
Research on damage detection and assessment of civil engineering structures based on DeepLabV3+ deep learning model
Structural Engineering and Mechanics, An Int＇l Journal
2024 .09
-
Performance Comparison of Mask R-CNN and Deep Crack Algorithms for Crack segmentation
한국콘크리트학회 학술대회 논문집
2023 .05
-
Automated Detection of Surface Cracks and Numerical Correlation with Thermal‑Structural Behaviors of Fire Damaged Concrete Beams
International Journal of Concrete Structures and Materials
2020 .05
-
주행 환경 인식을 위한 Multi-Task 딥러닝 모델
대한전자공학회 학술대회
2018 .06
-
다중 계층 self-attention을 이용한 도로 노면 파손 검출
대한전자공학회 학술대회
2021 .06
-
멀티 태스킹 딥러닝 기반의 도로 환경 인식과 객체 추적 기법 연구
한국자동차공학회논문집
2024 .01
-
Prediction of concrete spall damage under blast: Neural approach with synthetic data
Computers and Concrete, An International Journal
2020 .01
-
Wide Residual Networks for Semantic Segmentation
제어로봇시스템학회 국제학술대회 논문집
2018 .10
-
Twin models for high-resolution visual inspections
Smart Structures and Systems, An International Journal
2023 .04
이 논문의 저자 정보
최근 본 자료
댓글(0)
0