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

Abstract

The embodiment of the invention provides a turbulence image restoration method and device, terminal equipment and a computer readable medium. The method comprises the steps of obtaining a current to-be-processed turbulence image; determining a registration point of the current turbulence image to be processed; calculating a motion vector of each registration point according to an optical flow calculation method; performing non-uniform B spline interpolation on the motion vector, and converting the position of each pixel in the current turbulence image to be processed according to the interpolated motion vector to obtain a relative coordinate relative to a reference image; performing sub-pixel interpolation-based motion compensation on the relative coordinates to obtain a registered image of the current turbulence image to be processed, and performing superposition fusion on the registered image and a scene image to obtain a fused image; and performing detail enhancement processing on the fused image, so that a restored image can be obtained, and therefore, the turbulence image can be restored in real time, and the stability and identifiability of an image sequence can be effectively improved.

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