Method and system for removing video jitter

Abstract

The invention provides a method and a system for removing video jitter. The method comprises the following steps: 1. registering the current image frame in a video opposite to the adjacent image frame thereof; 2. accumulating trajectory information of the jitter generated in registration, and jittering the generated motion trail smoothly; and registering the current image frame in a direction opposite to the motion trail; 3. filling a blank area generated at the edge of the current image frame by an image frame adjacent to the current image frame; and 4. jumping to the next image frame of the current image frame, returning to the first step until all the image frames in the video are completely processed. The method and the system of the invention has quicker processing speed, is unrelated to the contrast ratio of the image, has relatively higher registering precision, ensures that the filled image has good continuity and consistency at the edge, and reduces trails of manual handling.

Description

technical field [0001] The invention belongs to the field of image processing, in particular, it relates to the technology of removing video shaking. Background technique [0002] When the camera equipment is fixed on a building or a pillar, it will vibrate when there is wind; it will also output jitter in places with vibrations such as machines (such as cars, airplanes, ships, etc.), heating and ventilation equipment, air conditioners, and PTZ pan / tilts The unstable video image, especially in the case of using a high-magnification lens, the degree of video shaking is more serious, which seriously affects the visual effect. For the video output by the camera device, the processing speed of the current video shake removal method often cannot meet the real-time requirement, or the resolution of the processed video is reduced. [0003] The primary task of video de-jittering is the registration between adjacent frame images, and the accuracy of registration will directly affect...

AI Technical Summary

Problems solved by technology

Among them, the SIFT corner detection and matching method has scale and rotation invariance, and can more accurately register images, but the computational complexity is high, and it is difficult to achieve real-time processing

The Harris and SUSAN corner detection algorithms are relatively fast and can detect the corners in the image more accurately, but when the contrast of the image is low or the image offset scale is large, the registration accuracy is low and the continuity of the edge and less consistent

Images