An Innovative Method for Locating the Welded Circular Seam on the Inner Surface of Cylinder Pipeline to Inspector Robot

Abstract

Locating the welded seam on the inner surface of a pipeline from the frame image captured by the monocular optical camera is a key and challenging problem in intelligentizing the defect inspection robot. Due to the lack of feature points and feature straight lines on the image of the welded seam, the existing visual odometry method cannot be used to locate the welded seam relative to the inspector robot. In this paper, an innovative method is proposed for locating the welded circular seam on the inner surface cylinder pipeline to inspector robot. In this method, the whole shape of the welded seam is retrieved from the frame captured by the monocular camera of the robot and is used as the feature for the location. Through combining the retried shape features and the moving velocity of the robot, the distance from the robot to the welded seam can be calculated quickly based on the optical imaging principle. Experiments show that our method can effectively locate the welded seam. Our method can used in intelligent pipeline inspector robot to locate the welded seam to defect test.