Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method for Extracting Moving Objects from Video Sequences

A technology for video sequences and moving objects, which is applied in image analysis, image enhancement, instruments, etc., can solve the problems of video data cannot be stored, manual processing, data increase, etc., and achieve the effect of extracting moving objects and suppressing ghosting problems

Active Publication Date: 2021-09-28
ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This growth has resulted in a massive increase in data, which means that video data cannot be stored or processed manually
[0003] Since the publication of the ViBe algorithm paper in 2011, the ViBe algorithm has been applied to the detection of moving objects in video sequences, but the ghosting problem in this technology (the detected moving objects do not correspond to any real moving objects
) will lead to misjudgment of downstream technology

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
  • A Method for Extracting Moving Objects from Video Sequences
  • A Method for Extracting Moving Objects from Video Sequences
  • A Method for Extracting Moving Objects from Video Sequences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific implementation manner of the present invention will be described in detail below in conjunction with the examples.

[0030] A video sequence-oriented moving target extraction method, the specific steps are as follows:

[0031] Step 1: Extract the first frame of the video sequence as the initialization image initMat, the image width is width, and the height is height;

[0032] Step 2: Extract the background RGB color of initMat, the specific steps are:

[0033] Step 2.1: Split the image initMat into n blocks seg using the region growing method i (i=1,2,3,…,n), each block has m i pixel points j i (j=1,2,3,...,m i ), the RGB values ​​of each pixel are

[0034] Step 2.2: Find all m i The maximum value of , recorded as max_i;

[0035] Step 2.3: Calculate the RGB average value of each block and record it as AR i 、AG i 、AB i ,Calculated as follows:

[0036]

[0037]

[0038]

[0039] Step 2.4: Calculate all seg according to formula (4) i wi...

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 video sequence-oriented moving target extraction method, comprising the following steps: step 1: extract the first frame of the video sequence as an initialization image initMat, the image width is width, and the height is height; step 2: extract the background RGB of initMat Color, step 3: merging AVGR, AVGG, AVGB into the ViBe algorithm, the beneficial effect of the present invention is: the present invention can automatically extract a single background pixel as a basis for judgment under the premise of a single background, and preferably suppress the ghost of the ViBe algorithm. It effectively realizes the moving target extraction for video sequences.

Description

technical field [0001] The invention is applied in a video sequence of a single background, automatically detects in the video sequence of this type, and distinguishes moving objects from static or slow-moving scene parts. Background technique [0002] As the world develops, the number of cameras available across the globe has increased dramatically. This growth has resulted in a massive increase in data, which means that video data cannot be stored or processed manually. [0003] Since the publication of the ViBe algorithm paper in 2011, the ViBe algorithm has been applied to the detection of moving objects in video sequences, but the ghosting problem in this technology (the detected moving objects do not correspond to any real moving objects.) will cause downstream Technical misjudgment. Contents of the invention [0004] In order to overcome the ghost problem existing in the ViBe algorithm, the present invention provides a single background initialization method and a...

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 Patents(China)
IPC IPC(8): G06T7/20G06T7/10
CPCG06T7/20G06T2207/10016G06T7/10
Inventor 刘远超吴宗林夏路何伟荣
Owner ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC