Method for recovering dynamic video background based on the space-time joint matrix

A joint matrix and background technology, which is applied in image data processing, instruments, calculations, etc., can solve the problems of unfixed viewing angle of the video screen and inability to model the background

Pending Publication Date: 2020-09-04
TIANJIN UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in most cases, the viewing angle of the video is not fixed, so for this type of dynamic video, it is impossible to accurately model the background

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for recovering dynamic video background based on the space-time joint matrix
  • Method for recovering dynamic video background based on the space-time joint matrix
  • Method for recovering dynamic video background based on the space-time joint matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The invention belongs to the field of computer vision and is a very important preprocessing step. Specifically, a method for recovering a background that does not contain a moving foreground from a video captured by a moving camera with an unfixed viewing angle.

[0064] In order to make up for the shortcomings of the existing technology, it is to achieve accurate background modeling of dynamic video stream data, and at the same time improve the spatial scalability of the model so that it can be applied to high-resolution videos. The technical solution adopted by the present invention is to decompose the nuclear norm item of the constraint batch processing implementation mode into a low-rank matrix, and transform the model into a form that can be processed by a single frame. At the same time, the affine transformation operator is embedded, and the model is iteratively solved by using the alternating direction algorithm. During the solution process, the viewing angle of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to video image processing, and aims to realize accurate background modeling of dynamic video stream data and improve the spatial expandability of a model, so that the dynamic video stream data can be applied to a high-resolution video. According to the technical scheme, a method for recovering the dynamic video background based on the space-time joint matrix comprises the steps that low-rank matrix decomposition is conducted on nuclear norm items of a constraint batch processing implementation mode, and a model is converted into a single-frame processing mode. Meanwhile,an affine transformation operator is embedded, iterative solving is conducted on the model through an alternating direction algorithm, in the solving process, the view angles of the videos are gradually unified, and dynamic video background recovery is achieved. The method is mainly applied to video image processing occasions.

Description

technical field [0001] The invention relates to video image processing, in particular to a method for restoring a dynamic video background based on a time-space joint matrix. Background technique [0002] In the field of computer vision, background modeling is a very important preprocessing technology, and it has extremely important applications in problems such as motion detection, target tracking, and behavior recognition. For a long time, the research on the background modeling method has never stopped, and its solution methods are emerging in endlessly. Initial research work independently estimated the pixel distribution of the background through various statistical models (such as median model, histogram model, Gaussian model, etc.), thereby classifying pixels as background components or foreground components. However, this type of method ignores the very important essential structural features of the video: the temporal similarity of the background and the spatial con...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00
CPCG06T5/007G06T2207/10016
Inventor 杨敬钰师雯李坤刘海军
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap