In this study, the three-phase missing region of interest area detection and damage localization methodology based on three-dimensional image coordinates was proposed. In Phase 1, the coordinate transformation is performed by the position and attitude information of the unmanned aerial vehicles and camera, and the coordinates of the center point of each acquired image are obtained with the distance information between the camera and the target surface. For Phase 2, the size of the field of view of every acquired image is calculated using the focal length and working distance of the camera. Finally, in Phase 3, the missing part of the region of interest area can be identified and any damage detected at the individual image level can also be localized on the whole inspection region using information about the sizes of the field of view in all images calculated in the previous phase. In order to demonstrate the proposed methodology, experimental validation was performed on the actual bridge pier and deck as well as the lab-scale concrete shear wall. In the tests, the missing area detection and damage localization results were compared with image stitching and human visual inspection results, respectively. Experimental validation results have shown that the proposed methodology identifies missing areas and damage locations within reasonable accuracy of 10 cm.

Key information for the maintenance and diagnosis of structures including bridges can be obtained from the processing of digital images acquired by unmanned aerial vehicle (UAV). However, lowquality images caused by various problems such as UAV movement, inspection environment, and camera parameters can lead to inappropriate structural evaluation due to the difficulty of digital image processing. Therefore, an appropriate assessment method for image quality considering the deterioration of the inspection image in the structural inspection procedure is required. In this study, a new image quality assessment (IQA) using a convolutional neural network (CNN) is proposed in consideration of various degradation factors that may occur in the structure inspection image. The first stage presents a method to obtain consistent quality against various interference factors of deterioration that may occur in inspection images. Adjusting the camera parameters minimizes the degradation of the inspection image. Subsequently, low-and high-quality images are distinguished according to the proposed image acquisition method. The second stage is the classification of the inspection dataset using the CNN-based image quality classifier model through training of data classified according to their quality. Experimental validation of the proposed method shows that the results are similar to the Human Visual System (HVS), which means subjective quality classification, and that the inspection image can be classified with more accurate and shorter processing time.

No abstract