Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Video foreground detection method

A technology of foreground detection and video, applied in CCTV system, image data processing, instrument, etc., can solve the problems of incomplete target detection and excessive value

Active Publication Date: 2017-03-08
上海悠络客电子科技股份有限公司
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

From the perspective of the human eye, when the VIBE algorithm selects the global threshold R, it must detect foreground pixels in the three intervals of 32-192, 0-32, and 192-255. Therefore, the value of the threshold R is too large. When detecting scenic spots, there will be problems with incomplete target detection

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
  • Video foreground detection method
  • Video foreground detection method
  • Video foreground detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] A video foreground detection method that can generate background images and increase the ability to distinguish closer gray levels.

[0028] Video image compression, encoding, public network transmission, and decoding processes will introduce a large number of jitter noises in image pixel values. These jumps lead to an increase in the R of the local image. according to figure 2 The relationship between the human eye's resolution ability and the gray level of the image can be divided into five intervals, namely [0,32), [32,64), [64,128), [128,192), [192,256) R value use R n express. R n The value of is the threshold value of human eye discrimination in the interval, the threshold value H for suppressing beating noise noise related. The relationship is shown in formula (3).

[0029] Rn=kΔs(n)+H noise (3)

[0030] Among them, n is the value of the gray value [0,255]; k is the gray threshold system, the value is [2,4], generally 3; H noise is the grayscale value ...

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 the technical field of detection of a moving target in a low-quality video, and especially puts forward a video foreground detection method by use of a VIBE (Visual Background Extractor) law. According to the method, a VIBE model is adopted, the R value is expressed in Rn, the value of Rn is related to the human eye resolution threshold and the jitter noise inhibition threshold H(noise) in an interval, and the relation is Rn=k*delta s(n)+H(noise), wherein n is the grey value [0, 255], k is a gray threshold system [2, 4], and H(noise) is the gray value jitter noise threshold in each gray interval. According to the invention, improvement is made based on the shortcomings of a VIBE model method, and a video foreground detection method which enables a background image to be generated and increases the ability to distinguish close gray scales is put forward.

Description

technical field [0001] The invention relates to the technical field of moving target detection in low-quality video, and in particular proposes a video foreground detection method by using the VIBE rule. Background technique [0002] Networking and intelligentization of video surveillance system is the mainstream research direction in the security field. With the development of artificial intelligence technology and the increase of human resource costs, the market's demand for intelligent video surveillance systems is increasing. According to the deployment position of the video intelligent algorithm calculation node, the intelligent video surveillance system can be divided into a front-end intelligent video surveillance system and a server-side intelligent video surveillance system. The front-end intelligent video surveillance system embeds intelligent algorithms into the front-end video image acquisition equipment, and directly performs intelligent analysis on the video i...

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): G06T7/11G06T7/254G06T7/136G06T7/194H04N7/18
CPCG06T2207/30232H04N7/18
Inventor 李生金刘冬冬吴旭宾
Owner 上海悠络客电子科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com