Method for splicing non-control point image

Abstract

The invention relates to a method for image mosaic without control points, which comprises the following steps: (1) acquiring an image sequence; (2) extracting a characteristic point set of each image in the image sequence; (3) searching homonymy point pairs of characteristic points between two adjacent images; (4) calculating a Homograph transformation relation between the adjacent images by using an RANSAC error-tolerant algorithm; and (5) using a continual multiplication formula and fusion technology to obtain mosaic results. Aiming at each characteristic point, the method can automatically collect a color channel with highest characteristic significance degree, so as to not only improve amount of the characteristic points greatly, but also improve significance and accuracy of the characteristic points. The method can be used as a correction method for human-computer interactive air photos to correct micro errors accumulated during mosaic. The method needs no control points, and has the advantages of high accuracy, low application cost and high efficiency.

Description

technical field [0001] The invention belongs to the technical field of computer vision image processing, in particular to a method for automatically and continuously splicing video frames of changing scenes into a complete image. This technology does not require camera pose and ground control point information, and video (or image) Sequence) arbitrary angle rotation, scale and perspective transformation, to realize a fully automatic color video image seamless mosaic technology. Background technique [0002] Automatic image stitching technology has a wide range of needs and applications in remote sensing survey, military reconnaissance, space exploration (such as image stitching on the surface of the moon and Mars), 360° panoramic image generation, and automatic stitching of UAV remote sensing images. Once there is rotation in the traditional image stitching process, interference factors such as scale and illumination transformation often require manual participation, which i...

AI Technical Summary

Problems solved by technology

[0006] 2. Automatic matching of feature points with the same name between stitched images or video frames, this process must be fast and robust

Many traditional registration and stitching methods have disadvantages such as poor stitching accuracy, low efficiency, and low degree of automation. Some require the attitude of the aircraft or camera and GPS information or the absolute coordinates of ground control points, which are difficult to provide in many cases. (For example, it is impossible to obtain GPS information during wartime; it is difficult to obtain the information of control points in unknown regions (such as the surface of Mars) in aerial photography), and some are difficult to resist the interference of rotation, scale change and illumination

Images