Background model based on multiple information integration

A background model and background technology, applied in the field of video processing, can solve problems such as high complexity, poor effect, dynamic background disturbance, etc., and achieve the effect of improving performance, accuracy and precision

Inactive Publication Date: 2012-01-11
BEIJING SAFE VISION TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 2) Dynamic background disturbance
Although some literature has tried in this regard, the effect is not very good
For example, there are literatures that try to describe the background model using color and gradient information, and use the color co-occurrence matrix to represent the color change of adjacent frames, but because it is unimodal, the performance of

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
  • Background model based on multiple information integration
  • Background model based on multiple information integration
  • Background model based on multiple information integration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Aiming at the problems existing in the prior art, the present invention describes the observation mode of each pixel by combining color information and spatial structure information; and further adopts the framework of mixed Gaussian model, and proposes a mixed Gaussian background model based on joint color information and spatial structure information . The pixel information is represented by the color located in the local area at each position, while the local spatial information is represented by the pixel grayscale feature.

[0037] The implementation method of background subtraction in the present invention mainly includes the following steps: for the current input image, calculate the current observation mode of each pixel by combining local spatial information and color information; compare the current observation mode of each pixel with all modes in the background model, and find The background model mode with the closest distance to the current observation mode...

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 background subtraction implementation method and device. The method comprises the following steps: calculating the current observation mode of each pixel of the current input image by combining local spatial information with color information; comparing the current observation mode of each pixel with all modes in a background model, and finding out a background model mode which is closest to the current observation mode distance; if the current observation mode distance is less than the scheduled threshold, judging the closest background model mode as a background, otherwise judging the closest background model mode as a foreground; and updating the background model according to the judgment conditions of the foreground and the background. Aiming at the problems in the prior art, in the method provided by the invention, the pixel information is combined with space structure information to describe the observation mode of each pixel, and a hybrid Gaussian model frame is adopted to build a hybrid Gaussian background model with the combination of the pixel information and the space structure information, thus the extraction performance of the foreground is greatly promoted, and the extractive precision and accuracy of the foreground are effectively improved.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a method and device for implementing background subtraction. Background technique [0002] Background subtraction is often called foreground extraction, motion detection, etc. It is one of the key technologies of low-level computational vision and video processing, and is widely used in video surveillance, intelligent transportation, industrial vision and other fields. Background subtraction is applied to the condition of a still camera, which means that the fixed scene in the field of view of the still camera is the background, and the object with relative motion is the moving foreground, and the background information is subtracted from the video image to obtain Extract motion foreground information. The actual changes in the background environment are very complicated. According to the reasons for the background changes, they can be divided into three categor...

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
IPC IPC(8): G06T7/20G06T7/194
Inventor 贾慧星
Owner BEIJING SAFE VISION TECH
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