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

Moving object detection and tracking method based on improved ViBe algorithm

A moving object, detection and tracking technology, applied in computing, image data processing, instruments, etc., can solve problems such as insufficient model abundance, high complexity of moving object tracking strategy, unsolvable "shadow" legacy problems, etc., to reduce computational complexity degree, reduce background noise and misjudgment probability, and improve the effect of background stability

Active Publication Date: 2016-09-07
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if there is a moving object or other disturbances in the first frame (such as video shake, strong light changes, etc.), the moving object will be misjudged during foreground detection
At the same time, using a single frame to build the entire background sample set will also make the model not rich enough
[0006] Second, the ViBe algorithm only updates the background model after the foreground detection, so the video noise cannot enter the model, enriching the background model, making the model less resistant to noise
Moreover, the prospect of a certain misjudgment cannot be updated quickly, so that the prospect of this misjudgment has been misjudged many times
[0007] Third, the ViBe algorithm cannot solve the legacy problems of "shadow"
[0008] For the above deficiencies of the ViBe algorithm and the high complexity of most existing moving object tracking strategies, the present invention proposes a moving object detection and tracking method based on the improved ViBe algorithm

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
  • Moving object detection and tracking method based on improved ViBe algorithm
  • Moving object detection and tracking method based on improved ViBe algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0083] Such as figure 1 Shown, be a kind of overall flowchart of the moving object detection and tracking method based on improved ViBe algorithm of the present invention, comprise the following steps:

[0084] Step S1: Compare the input frame with the temporary background image constructed from the first three frames of the current frame to determine whether the frame is stable and the visual

[0085] If the video is stable, then proceed to step S2 background model initialization, otherwise wait for the background to be stable, such as figure 2 shown;

[0086] 1-1) Use the first three frames of the current frame I to construct a temporary background image I', namely:

[0087] I'=w 1 I 1 +w 2 I 2 +w 3 I 3 ,

[0088] In the formula, I 1 , I 2 , I 3 For the first three frames of the current frame I, w 1 、w 2 、w 3 The weight set for each frame, and w 1 +w 2 +w 3 =1. To make I' adapt to real-time changes in the background, set w 1 >w 2 >w 3 .

[0089] 1-2) ...

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 moving object detection and tracking method based on an improved ViBe algorithm, and the method specifically comprises the following steps: S1, employing a strategy for judging the stability of a video before the initialization of a ViBe background model, and employing a plurality of stable input frames, which do not need to be continuous, for constructing the background model after the stabilizing of the video; S2, carrying out the first background model correction after ViBe extracts a foreground image; S3, carrying out the second background model correction after the detection and tracking of a moving object; S4, carrying out the matching of a moving object frame set in a current frame with a moving object dynamic rectangular frame set constructed by a moving object frame set in a former time period through employing geometric comparison during the positioning and tracking of the moving object. The method improves the background stability, reduces the background noise and misjudgment probability, solves a shadow leftover problem, and reduces the calculation complexity of positioning and tracking.

Description

technical field [0001] The invention relates to the field of computer video image processing, in particular to a moving object detection and tracking method based on an improved ViBe algorithm. Background technique [0002] The detection and tracking of moving objects is one of the important links of the intelligent surveillance video system. It is located at the bottom of the whole system and is the basis of subsequent links such as target recognition and target classification. Moving object detection refers to extracting the moving target foreground from the video stream background. Moving object tracking refers to the continuous tracking of moving objects for the next step of processing. [0003] The ViBe (Visual background extractor) algorithm was first proposed by Olivier Barnich and Marc Van Droogenbroeck in 2009. It is an algorithm for pixel-level video background modeling or foreground detection. The idea is to first store a sample set for each pixel, and the sampl...

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): G06T7/20
CPCG06T2207/10016
Inventor 贺前华李悦馨庞文丰
Owner SOUTH CHINA UNIV OF TECH
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