Study of filming condition for deep learning based crack detection method
Last modified: 2023-06-05
Abstract
However, some local public organizations have problems that insufficient manpower relative to the number of bridges to manage, as well as insufficient funding for maintenance. Thus, these organizations are unable to perform routine close visual inspections. Specific problems include “notably less staff and consulting technicians relative to the number of bridges to be managed” and “high inspection cost preventing from funding for repair.”
As issues with the continuing close visual inspection of bridges are surfacing, the remote imaging system is expected to become a new inspection method that replaces close visual inspection.
The practical potential of bridge inspections using images captured with a super-high-resolution camera was examined. A super-high-resolution camera enables us to take a wide area picture of a target bridge from a long distance. An image processing method could improve the efficiency of image-based inspection method. For example, a deep learning-based image processing method could extract a damaged area on a surface of a bridge automatically with high accuracy faster than human inspection. In general, the accuracy of an image processing method is affected by the quality of an input image. Filming conditions are one of the factors that determine the quality of a photo image. It is important to evaluate the effect of filming conditions to improve the reliability of an image processing method. In this paper, we evaluate the effect of the filming conditions for an image processing method by comparing the results of a deep learning-based crack detection method.