Turbulence image restoration method, device, terminal device and computer readable medium

Abstract

Embodiments of the present invention provide a turbulence image restoration method, device, terminal equipment and computer-readable medium. The method includes: acquiring the current turbulence image to be processed; determining the registration point of the current turbulence image to be processed; and determining the registration point of the current turbulence image to be processed according to the optical flow. The calculation method calculates the motion vector of each registration point; performs non-uniform B-spline interpolation on the motion vector, and transforms the position of each pixel in the current turbulence image to be processed according to the interpolated motion vector to obtain the relative position relative to the reference image. coordinates; perform motion compensation based on sub-pixel interpolation on the relative coordinates to obtain a registration image of the current turbulence image to be processed, and superimpose and fuse the registration image with the scene image to obtain a fused image; Detail enhancement processing is performed to obtain the restored image, so that the turbulence image can be restored in real time, effectively improving the stability and recognizability of the image sequence.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a turbulent image restoration method, device, terminal equipment and computer readable medium. Background technique [0002] In applications such as aerial mapping and remote detection, photoelectric imaging systems are affected by atmospheric turbulence, and the collected images will appear distorted, jittery, and flickering, which seriously affects the reliability and stability of the entire detection system. False negatives, false positives, and target loss during target tracking occur. [0003] The turbulent image restoration method is based on the study of the cause of image degradation, according to certain prior knowledge, using the degraded image to establish a corresponding degradation model, and then performing the opposite operation on the degraded image according to the established model, so as to restore the original target image the goal of. S...

AI Technical Summary

Problems solved by technology

However, on the one hand, the computational complexity of these methods cannot meet the real-time requirements of remote detection, and it is difficult to implement engineering on the hardware platform of today's detection terminals; on the other hand, these methods need to rely on the prior information of the image. very limited range

Images