본 논문에서는 프리팹 구조물의 품질관리를 위한 딥러닝 및 비전센서 기반의 조립 성능 평가 모델을 개발하였다. 조립부 검출을 위 해 인코더-디코더 형식의 네트워크와 수용 영역 블록 합성곱 모듈을 적용한 딥러닝 모델을 사용하였다. 검출된 조립부 영역 내의 볼트 홀을 검출하고, 볼트홀의 위치 값을 산정하여 k-근접 이웃 기반 모델을 사용하여 조립 품질을 평가하였다. 제안된 기법의 성능을 검증 하기 위해 조립부 모형을 3D 프린팅을 이용하여 제작하여 조립부 검출 및 조립 성능 예측 모델의 성능을 검증하였다. 성능 검증 결과 높은 정밀도로 조립부를 검출하였으며, 검출된 조립부내의 볼트홀의 위치를 바탕으로 프리팹 구조물의 조립 성능을 5% 이하의 판별 오차로 평가할 수 있음을 확인하였다.

Severe earthquakes can cause damage to society both socially and economically. An appropriate initial response can alleviate damage from severe earthquakes. In order to formulate an appropriate initial response, it is necessary to identify damage situations in societies; however, it is difficult to grasp this information immediately after an earthquake event. In this study, an earthquake damage assessment methodology for buildings is proposed for estimating damage situations immediately after severe earthquakes. A response spectrum database is constructed to provide response spectra at arbitrary locations from earthquake measurements immediately after the event. The fragility curves are used to estimate the damage of the buildings. Earthquake damage assessment is performed from the response spectrum database at the building scale to provide enhanced damage condition information. Earthquake damage assessment for Gyeongju city and Pohang city were conducted using the proposed methodology, when an earthquake occurred on September 12, 2016, and November 15, 2017. Results confirm that the proposed earthquake damage assessment effectively represented the earthquake damage situation in the city to decide on an appropriate initial response by providing detailed information at the building scale.

Bridge inspection based unmanned aerial vehicle (UAV) has received considerable attention due to its several advantages such as reliability and safety as well as saving time and cost. An unmanned inspection equipment for bridge inspection is composed of UAV and imaging devices such as RGB cameras and infrared cameras. However, many challenging issues should be solved in order to apply this technology to the field. In this paper, an UAV based crack detection method is investigated. To detect the cracks, the image processing techniques with deep learning algorithm are used. To build the spatial information of aging bridge, 3D point cloud based background model is generated.