Defect quantification method based on fusion of three-dimensional camera and neural network and application thereof

Abstract

The invention relates to the technical field of image processing, and discloses a defect quantification method based on fusion of a three-dimensional camera and a neural network and application thereof. The defect quantification method comprises the following steps: step A, cutting a grayscale image and point cloud data of a relatively large area acquired by a three-dimensional camera into a relatively small area related to a defect to obtain a grayscale image and point cloud data of the relatively small area; b, performing curved surface fitting on the cut point cloud data of the small area to obtain a smooth curved surface model; step C, using an instance segmentation neural network model to process the grayscale image of the small area to obtain a corresponding mask image; step D, extracting sub-point cloud data of the defect edge from the point cloud data of the small area according to the defect edge on the mask pattern; and step E, performing difference calculation on the sub-point cloud data and the smooth curved surface model to obtain geometric information of the defect. The calculation method is simple and high in calculation efficiency and accuracy.

Images