Anti-jitter image processing method and device, electronic device and storage medium

Abstract

The invention relates to an anti-jitter image processing method and device, an electronic device and a storage medium. The method comprises the following steps: acquiring a current actual attitude of the imaging equipment at a current shooting moment when a current frame of original image is shot, and acquiring a plurality of reference actual attitudes of the imaging equipment at a plurality of shooting moments when a plurality of frames of original images adjacent to the current frame of original image are shot; executing path smoothing processing based on the current actual attitude and the plurality of reference actual attitudes so as to determine a current virtual attitude after path smoothing at the current shooting moment; performing coordinate transformation on a current frame original image shot in the current actual attitude under the pixel coordinate system to a position where the current frame original image is estimated when shooting in the current virtual attitude so as to obtain a current frame first correction image; and determining a current frame result image based on the current frame first corrected image. The method has the advantages of low cost, high efficiency and stable correction effect.

Description

technical field [0001] The present application relates to the technical field of anti-shake image processing, and in particular to an anti-shake image processing method, device, electronic equipment and storage medium. Background technique [0002] In daily life, when mobile electronic devices such as handheld, wearable or vehicle-mounted devices shoot videos, it is inevitable that the shake of the electronic device will lead to adverse conditions such as blurred video images, which makes the video display screen look and feel unsatisfactory, and even Affects subsequent analysis and recognition of video images. In order to reduce or eliminate the influence of electronic device shake on the captured video, many video anti-shake technologies have been developed currently. [0003] The current mainstream video anti-shake technology can be divided into mechanical anti-shake, optical anti-shake, electronic anti-shake and digital anti-shake and other categories. Mechanical anti-...

AI Technical Summary

Problems solved by technology

Mechanical anti-shake can improve the shooting effect by setting up the shooting equipment on a stable gimbal, such as the handheld gimbal commonly used for outdoor shooting. Although this technology is effective, the gimbal equipment is generally expensive, so it is usually only used in professional photography.

Optical anti-shake can use the built-in movable parts of electronic equipment, such as micro-heads, to compensate the jittering optical path, thereby reducing the blur caused by shaking in the shooting picture. This anti-shake technology is stable, but it also requires equipment Hardware support is therefore more expensive

Digital anti-shake can only use digital image processing technology to operate the captured image sequence, and achieve anti-shake through image feature matching, motion information extraction, and image transformation methods, but image feature matching is limited by image content. , scenes with small motion range can get relatively good processing results, but once the picture content is single and blurred, matching errors are prone to occur, resulting in poor processing results, so this technology has the defect of low stability

Images