Video background recovery method based on movement information and matrix completion

Abstract

The invention belongs to the field of computer vision, and aims to provide a simple and practical background extracting method. The technical scheme adopted by the invention is as follows: a video background recovery method based on movement information and matrix completion comprises the steps of adopting movements of a moving object between frames and frames through optical flow detection, detecting the movement information to generate weight matrixes, and arranging the weight matrixes according to column vectors to generate a total weight matrix; then, arranging all sampled frames according to the column vectors to form original data array matrixes; multiplying observation matrixes and the total weight matrix according to elements to obtain the observation matrixes; after that, obtaining the completed observation matrixes through the matrix completion; finally, recovering each array of the matrixes according to the size of original sampled frames to obtain a background image. The method is mainly applied to background extraction.

Description

Technical field [0001] The invention belongs to the field of computer vision, and relates to adopting optical flow to detect motion information and matrix filling to realize background extraction. Specifically, it involves a video background restoration method based on motion information and matrix filling. Background technique [0002] The use of cameras has increased a lot in the past decade. But these growths have led to the expansion of data, which means that it is no longer feasible to store or process data manually. In order to automatically detect, store, and track moving targets from videos, researchers have proposed some feasible methods. A simple moving target detection algorithm uses one current frame after another in the video sequence to compare with a stable background frame. This is the mainstream background restoration algorithm. They can standardize to build a background model, then compare it with the current frame, and detect when there is a big difference i...

AI Technical Summary

Problems solved by technology

But since the values ​​of the pixel background are replaced on a first-in-first-out basis, this can still be problematic in fine-grained discussions unless it stores a large number of pixel samples, e.g. about fast and slow motion in the background

Images