Abstract
The ministry of land, infrastructure, transportation and tourism proposed the road tunnel periodic inspection in the year 2014. The manual indicates that the frequency of the periodic inspection is once every five years. The inspection are mainly conducted by visual inspection. Therefore, there is a need for the automation in order to improve the efficiency of the inspection procedure. The authors have developed an inspection vehicle for tunnel lining concrete. The vehicle takes continuously scanned images of tunnel wall by using digital video cameras and lighting devices. In previous studies, the authors developed an automatic image stitching method by image processing techniques in order to generate panoramic images of tunnel wall from the scanned images. However, the accuracy of the stitching method was insufficient. The study proposes the improved image stitching method based on a local search algorithm. Furthermore, application to an existing tunnel is presented so as to demonstrate the accuracy and processing time of the proposed method.
