Foreground extracting method suitable for dynamic background

A technology of foreground extraction and dynamic background, applied in the field of computer video processing, can solve problems such as scenes that are not suitable for large-scale sudden changes, and achieve the effect of improving the update rate and overcoming disturbance.

Active Publication Date: 2013-07-24
联通(上海)产业互联网有限公司
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods can adapt to some small perturbations, they are not suitable for scenarios with large-scale mutations.

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
  • Foreground extracting method suitable for dynamic background
  • Foreground extracting method suitable for dynamic background
  • Foreground extracting method suitable for dynamic background

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] The video sequences used in this embodiment are the waving tree and light switching test sequences under Wallflower Paper.

[0030] like figure 1 As shown, the foreground extraction method under the dynamic background involved in this embodiment includes the following specific steps:

[0031] The first step: the initialization of the model. In the initial K+2 (K represents the number of models per pixel, set by the designer, generally K takes 3-5) frame pictures, from the 2nd frame to the K+1th frame, for each Calculate K SLBP-AM histograms for each pixel (the specific calculation method is shown below), m 0 ,m 1 ,...,m K-1 , and assign a weight ω to each histogram 0 ,ω 1 ,...,ω K-1 , where ω i ∈[0,1], and satisfy ω 0 +ω 1 +...+ω K-1 =1. Arrange the K histograms in descending order of weight, and select the first B as the background histogram, and the selection of B satisfies: ω 0 +...+ω B-1 >T B T B ∈[0,1], T B is the threshold value, set by the design...

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 discloses a foreground extracting method suitable for a dynamic background, which comprises the following steps of storing an adjacent image, combining spatial texture information and temporal motion information of pixels, carrying out comparison to form a dynamic texture, extracting an ellipsoid stereoscopic space for describing the dynamic texture, and dividing the stereoscopic space into three orthogonal planes to respectively reflect space characteristics and time characteristics of the pixels; meanwhile, carrying out texture description on the three planes by using an LBP (Local Binary Pattern) descriptor and weighting and summing three texture characteristics to form an SLBP-AM descriptor; and finally, carrying out separation on a foreground and the background by establishing a background model for the SLBP-AM descriptor, and completing updating of the model. The foreground extracting method disclosed by the invention utilizes the spatial texture information, can overcome little disturbance in the background and also fuses the motion information, so that scenes which are rapidly and greatly changed have the same motion mode before and after the change, and thus, the updating speed of the background is improved.

Description

technical field [0001] The invention belongs to the technical field of computer video processing, and in particular relates to a foreground extraction method, in particular to a foreground extraction method under a dynamic background. Background technique [0002] At present, computer vision technology is playing an increasingly important role in urban video surveillance, such as pedestrian detection, crowd density analysis, and abnormal event detection. Foreground detection, as the premise of these computer vision technology research, still faces great challenges due to complex background changes, such as shaking, lighting changes, shadow effects, etc. At present, the work on foreground detection is mainly divided into two categories: one is the traditional detection method based on a single pixel and only considers the gray value of the pixel itself. Because this method ignores the influence of adjacent pixels on it, it cannot overcome the disturbance of the background ve...

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): G06T7/20
Inventor 杨华尹海燕苏航
Owner 联通(上海)产业互联网有限公司
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