Video image stabilization method based on three-dimensional space-time image estimation technology

Abstract

The invention discloses a video image stabilization method based on a three-dimensional space-time image estimation technology. Original data are collected through a vidicon, the collected original data are preprocessed to be sequential frame sequences, interframe movement conditions are estimated by means of space similarity between a current frame and a reference frame, the jitter amount of each frame is obtained by means of the minimum distance criterion, a set of jitter vectors can be obtained through multi-frame processing, and the obtained set of jitter vectors is used for representing the moving conditions of the vidicon in a time domain; according to all the jitter estimation information in each frame, the overall moving condition of the current frame is obtained comprehensively, space reconstruction is carried out on an original scene frame image through a motion estimation result, the jitter amount is eliminated, and a stabilized image sequence is obtained. The video image stabilization method is used for eliminating jitter influences, video contents are stabilized, the video image stabilization method is based on three-dimensional space-time image estimation, and the defect that field depth changes cannot be processed in a two-dimensional scene stabilization image can be effectively overcome.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a video image stabilization method based on 3D space-time image estimation technology. Background technique [0002] With the development and popularization of video recording equipment, the coverage of the monitoring system is also rapidly expanding. It has a wide range of applications in both military and civilian fields. The platforms (airborne, indoor monitoring, etc.) and video types (visible light, Infrared, etc.) are varied. Regardless of the platform and type of video data, clear and stable content is a necessary prerequisite for obtaining interesting information. In practical applications, due to various influences of internal and external environments, such as air flow, carrier platform movement, etc., the captured video content will shake undesired by the observer, resulting in degradation of visual effects. When the jitter noise is serious, even Unable to g...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to make up for the defects of the prior art, solve the problem of video scene jitter caused by the system itself and external factors during video acquisition, and provide a video stabilization method based on 3D space-time image estimation technology to eliminate jitter Affects, Stabilizes Video Content

Images