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.
Hybrid fuzzy-based sliding-mode control approach, optimized by genetic algorithm for quadrotor unmanned aerial vehicles
