Rapid splicing method and system for workpiece images with sparse feature points

Abstract

The invention relates to the technical field of image stitching. According to the rapid splicing method and system for the workpiece images with the sparse feature points, a laser is used for projecting graphic signs in view overlapping areas of cameras, stable sign points with obvious features are provided, the size of the overlapping areas between the cameras is reduced while the image splicingprecision is improved, and the image processing speed is increased. According to the technical scheme, therapid splicing system for the workpiece images with the sparse feature points includes a plurality of strip-shaped light sources which are arranged on the two sides of a workpiece respectively so as to provide illumination conditions for an image capturing system, a plurality of industrial cameras which are used for detecting the workpiece, a plurality of lasers installed between the industrial cameras, a controller for controlling the strip-shaped light source and the laser device, and anindustrial personal computer which is electrically connected with the industrial personal computer so as to correct a shot image; The rapid splicing method for the workpiece images with the sparse feature points. The method comprises the steps of S1, image acquisition, S2, image preprocessing, S3, feature point detection matching and S4, image splicing fusion.

Description

technical field [0001] The present invention relates to the technical field of image stitching, and more specifically, to a method and system for quickly stitching workpiece images with sparse feature points. Background technique [0002] Image mosaic technology is a technology that stitches and fuses a group of images into a large field of view and high resolution image according to certain rules. First, it is a very important research direction in the field of image processing. [0003] Image stitching methods can be roughly divided into model-based methods, transform domain-based methods, gray-level correlation-based methods and feature-based methods. Among them, feature-based matching methods are currently used more, such as HARRIS, PCA-SIFT, SURF, and ORB. [0004] Compared with other image stitching methods, the feature-based matching method has the characteristics of high precision, fast and effective, and wide applicability, but on workpieces with sparse feature po...

AI Technical Summary

Problems solved by technology

[0004] Compared with other image stitching methods, the feature-based matching method has the characteristics of high precision, fast and effective, and wide applicability, but on workpieces with sparse feature points, such as sheet metal, wooden boards, etc., there are no particularly obvious texture features , it is difficult to find the feature point of the device, and the feature-based matching method is difficult to realize the stitching of such images

The feature-based matching method also requires a large overlapping area between the images to be stitched, which greatly wastes the field of view of the camera. Under the same image acquisition conditions, more industrial cameras need to be used, and the image processing time will also increase. The increase of the number of drawing frames will increase the measurement time of large-sized workpieces, making it difficult to realize online measurement of large-sized components

Images