Image attitude correction method, image attitude correction device, and terminal

Abstract

The invention discloses an image attitude correction method, an image attitude correction device, and a terminal. The method comprises the following steps: after the terminal receives an input image,acquiring 2M pixel points of the input image, then calculating a forward mapping matrix of the input image; further performing out-of-bounds determination based on the coordinates of the 2M pixel points forward-mapped, and eliminating the out-of-bounds by adjusting the position of the corrected image of the input image when there is an out-of-bounds; then calculating, by the terminal, an inverse mapping matrix of the input image according to the coordinates of the 2M pixel points before and after the posture correction; after deforming the input image according to the inverse mapping matrix, outputting the image by the terminal. On one hand, the application converts the input image from a forward mapping to a reverse mapping, which can reduce power consumption when the image is deformed. On the other hand, the application not only can perform the out-of-bounds judgment and the out-of-bounds adjustment efficiently, but also does not reduce the resolution of the output image.

Description

technical field [0001] The present application relates to the field of terminals, and in particular to an image pose correction method, device and terminal. Background technique [0002] When a user uses a handheld terminal to shoot a video, shaking of the user's hand and body movement causes the posture of the handheld terminal to change, and the posture change of the handheld terminal causes the picture of the captured video to shake. Specifically, the first frame image of the video is as figure 1 As shown in Figure 1A, the image of object W is located in the middle of the screen. The posture of the handheld terminal is always changing, so that the second frame of the video image is as follows figure 1 As shown in 1B, the image of the object W is located at the upper right of the screen. The third frame image of the video is as figure 1 As shown in 1C, the image of the object W is located on the right side of the screen. As the posture of the handheld terminal changes...

AI Technical Summary

Problems solved by technology

The existing image posture correction methods not only have complex algorithms and high power consumption, but also have unsatisfactory correction effects, resulting in poor video anti-shake effects

Images