Image processing method, device and readable storage medium

Abstract

The present disclosure relates to an image processing method, device, and readable storage medium. The method includes acquiring a plurality of sequence images to be processed; wherein, the plurality of sequence images are acquired by an image acquisition device during movement, and the image acquisition device has pre-calibrated the first parameter; according to the first parameter, respectively determine the first coordinates corresponding to the feature points in each sequence of images; in the case of determining that the feature points are not on the same plane according to the first coordinates, the calibration parameters of multiple sequence images are determined by The first parameter is adjusted to the second parameter; according to the second parameter, the second coordinates corresponding to the feature points in each sequence image are respectively determined; when the feature points are determined to be on the same plane according to the second coordinates, multiple sequence images are performed. Splicing processing to obtain a spliced ​​image. The image processing method according to the embodiment of the present disclosure can effectively reduce the degree of distortion of the spliced ​​image.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to an image processing method, device and readable storage medium. Background technique [0002] Imaging spectrometer is a sensor that combines spectral technology and imaging technology to obtain spatial information and spectral information at the same time. Imaging spectrometers work in two common ways: push-broom and swing-broom. In the push-broom working method, the UAV flies over the target area at an appropriate speed, and then performs data cube synthesis and image stitching on the captured images. [0003] In the image stitching process corresponding to the push-broom type of work, affine transformation is usually used as the geometric transformation model between images, but the premise of doing this is that the camera is always shooting vertically to the ground to ensure that the pose does not change, but During the actual flight, due to the disturb...

AI Technical Summary

Problems solved by technology

[0003] In the image stitching process corresponding to the push-broom type of work, affine transformation is usually used as the geometric transformation model between images, but the premise of doing this is that the camera is always shooting vertically to the ground to ensure that the pose does not change, but During the actual flight, due to the disturbance of weather and other factors, it is difficult to ensure that the camera is always shooting vertically to the ground, so there may be errors in the pose between the two captured images. After shooting multiple images continuously, the accumulated pose error may be Make the spliced ​​image produce obvious distortion

Images