Night vision anti-corona video processing method based on heterogeneous image fusion

Abstract

The invention discloses a night vision anti-corona video processing method based on heterogeneous image fusion. According to the method, the continuous optimal cosine included angle threshold of the video content is determined by researching the cosine included angle theta of the feature vectors of the two frames of images and the correlation between the non-linear correlation information entropyNCIE and the frame removal rate, redundant frames in a video sequence are abandoned, and only anti-corona fusion processing is performed on reserved frames, so that the processing efficiency of the algorithm can be greatly improved; the problem of data expansion caused by a night vision anti-corona video fusion method in an information fusion process is solved; the original frame numbers of the extraction frames are reserved as time marks, the number of frames to be inserted between the extraction frames is determined, and the video frame rate after frame removal is recovered; the motion vector of the object is calculated by utilizing the inter-frame content difference, and the motion vector between the to-be-interpolated frame and the reference frame is obtained by endowing different self-adaptive weights to the reference motion vector, so that the to-be-interpolated frame image synchronous with the original video is constructed, and the problem that the content of the video after frame interpolation is not synchronous with the content of the original video is solved.

Description

technical field [0001] The invention belongs to the field of night vision anti-halation technology, and in particular relates to a method for extracting and compensating and interpolating frames of heterogeneous anti-halation fusion video, and in particular to a night vision anti-halation video processing method for heterogeneous image fusion. Background technique [0002] Through the infrared and visible light image fusion technology, the halo in the night vision image can be eliminated, the color and detail information of the image can be improved, and the imaging quality of the night vision image can be improved. Its development has gone through two stages. The early adoption of color space and spatial multi-resolution The fusion method of single transformation, such as single transformation, has the advantages of simple algorithm and fast processing speed, but there are problems such as incomplete halo elimination and blurred edge contour information in the fusion image; ...

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem that the night vision anti-halation fusion method has stuck and discontinuous playback when processing video images, and it is difficult to achieve the visual effect required by human eyes, and designs a night vision anti-halation video fusion of heterogeneous images. A processing method for improving night vision anti-halation video image fusion efficiency and improving the visual effect of night vision anti-halation fusion video

Images