Airplane surface hole positioning measurement method based on two-dimensional image and three-dimensional point cloud

The invention discloses an aircraft surface hole positioning and measuring method based on a two-dimensional image and a three-dimensional point cloud, and belongs to the technical field of aircraft defect detection. Firstly, a binocular structured light camera is used for collecting a two-dimensional image and three-dimensional point cloud data of the surface of an aircraft to be overhauled; for the two-dimensional image, positioning hole defects by adopting a YOLOX target detection algorithm; mapping the hole defect two-dimensional coordinate frame into a three-dimensional point cloud through camera calibration, stereo matching and spatial three-dimensional coordinate solution, and intercepting a target point cloud; downsampling is realized by using a voxelization grid method, and the number of point clouds is controlled; and realizing hole fitting and measurement of the three-dimensional point cloud based on an RANSAC algorithm, and obtaining space coordinates, area and depth information of hole defects. A