An image mosaicking method base on the curvature of cost curve for tunnel lining inspection

Abstract

The paper proposes an image mosaicking method for tunnel lining inspection. The conventional methods only used the cost value of the pixel being processed based on similarity metric to estimate an image-matching location. To improve the image-mosaicking efficiency, the curvature metric has adapted to improve matching point accuracy. Experimental results for an actual tunnel demonstrate that the curvature measurement can select the precise matching points accurately for assisting defect inspection without depending on the speed of inspection vehicle.